Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-29 19:47:54 +01:00
Code Issues Releases Wiki Activity

Merge branch 'master' into openload-phantomjs-method

Browse Source
This commit is contained in:
Tithen-Firion 2017-05-04 11:00:06 +02:00 committed by GitHub
commit c89267d31a
99 changed files with 2116 additions and 684 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE.md vendored
View File

@ -6,8 +6,8 @@
--- ---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.04.15*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. ### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.05.01*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.04.15** - [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.05.01**
### Before submitting an *issue* make sure you have: ### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[debug] User config: [] [debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.04.15 [debug] youtube-dl version 2017.05.01
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [debug] Proxy map: {}

2
.gitignore vendored
View File

@ -35,8 +35,8 @@ updates_key.pem
*.mkv *.mkv
*.swf *.swf
*.part *.part
*.ytdl
*.swp *.swp
test/testdata
test/local_parameters.json test/local_parameters.json
.tox .tox
youtube-dl.zsh youtube-dl.zsh

1
AUTHORS
View File

@ -211,3 +211,4 @@ Juanjo Benages
Xiao Di Guan Xiao Di Guan
Thomas Winant Thomas Winant
Daniel Twardowski Daniel Twardowski
Jeremie Jarosh

126
ChangeLog
View File

@ -1,3 +1,129 @@
version <unreleased>
Extractors
+ [cda] Support birthday verification (#12789)
* [leeco] Fix extraction (#12974)
version 2017.05.01
Core
+ [extractor/common] Extract view count from JSON-LD
* [utils] Improve unified_timestamp
+ [utils] Add video/mp2t to mimetype2ext
* [downloader/external] Properly handle live stream downloading cancellation
(#8932)
+ [utils] Add support for unicode whitespace in clean_html on python 2 (#12906)
Extractors
* [infoq] Make audio format extraction non fatal (#12938)
* [brightcove] Allow whitespace around attribute names in embedded code
+ [zaq1] Add support for zaq1.pl (#12693)
+ [xvideos] Extract duration (#12828)
* [vevo] Fix extraction (#12879)
+ [noovo] Add support for noovo.ca (#12792)
+ [washingtonpost] Add support for embeds (#12699)
* [yandexmusic:playlist] Fix extraction for python 3 (#12888)
* [anvato] Improve extraction (#12913)
* Promote to regular shortcut based extractor
* Add mcp to access key mapping table
* Add support for embeds extraction
* Add support for anvato embeds in generic extractor
* [xtube] Fix extraction for older FLV videos (#12734)
* [tvplayer] Fix extraction (#12908)
version 2017.04.28
Core
+ [adobepass] Use geo verification headers for all requests
- [downloader/fragment] Remove assert for resume_len when no fragments
downloaded
+ [extractor/common] Add manifest_url for explicit group rendition formats
* [extractor/common] Fix manifest_url for m3u8 formats
- [extractor/common] Don't list master m3u8 playlists in format list (#12832)
Extractor
* [aenetworks] Fix extraction for shows with single season
+ [go] Add support for Disney, DisneyJunior and DisneyXD show pages
* [youtube] Recognize new locale-based player URLs (#12885)
+ [streamable] Add support for new embedded URL schema (#12844)
* [arte:+7] Relax URL regular expression (#12837)
version 2017.04.26
Core
* Introduce --keep-fragments for keeping fragments of fragmented download
on disk after download is finished
* [YoutubeDL] Fix output template for missing timestamp (#12796)
* [socks] Handle cases where credentials are required but missing
* [extractor/common] Improve HLS extraction (#12211)
* Extract m3u8 parsing to separate method
* Improve rendition groups extraction
* Build stream name according stream GROUP-ID
* Ignore reference to AUDIO group without URI when stream has no CODECS
* Use float for scaled tbr in _parse_m3u8_formats
* [utils] Add support for TTML styles in dfxp2srt
* [downloader/hls] No need to download keys for fragments that have been
already downloaded
* [downloader/fragment] Improve fragment downloading
* Resume immediately
* Don't concatenate fragments and decrypt them on every resume
* Optimize disk storage usage, don't store intermediate fragments on disk
* Store bookkeeping download state file
+ [extractor/common] Add support for multiple getters in try_get
+ [extractor/common] Add support for video of WebPage context in _json_ld
(#12778)
+ [extractor/common] Relax JWPlayer regular expression and remove
duplicate URLs (#12768)
Extractors
* [iqiyi] Fix extraction of Yule videos
* [vidio] Improve extraction and sort formats
+ [brightcove] Match only video elements with data-video-id attribute
* [iqiyi] Fix playlist detection (#12504)
- [azubu] Remove extractor (#12813)
* [porn91] Fix extraction (#12814)
* [vidzi] Fix extraction (#12793)
+ [amp] Extract error message (#12795)
+ [xfileshare] Add support for gorillavid.com and daclips.com (#12776)
* [instagram] Fix extraction (#12777)
+ [generic] Support Brightcove videos in <iframe> (#12482)
+ [brightcove] Support URLs with bcpid instead of playerID (#12482)
* [brightcove] Fix _extract_url (#12782)
+ [odnoklassniki] Extract HLS formats
version 2017.04.17
Extractors
* [limelight] Improve extraction LimelightEmbeddedPlayerFlash media embeds and
add support for channel and channelList embeds
* [generic] Extract multiple Limelight embeds (#12761)
+ [itv] Extract series metadata
* [itv] Fix RTMP formats downloading (#12759)
* [itv] Use native HLS downloader by default
+ [go90] Extract subtitles (#12752)
+ [go90] Extract series metadata (#12752)
version 2017.04.16
Core
* [YoutubeDL] Apply expand_path after output template substitution
+ [YoutubeDL] Propagate overridden meta fields to extraction results of type
url (#11163)
Extractors
+ [generic] Extract RSS entries as url_transparent (#11163)
+ [streamango] Add support for streamango.com (#12643)
+ [wsj:article] Add support for articles (#12558)
* [brightcove] Relax video tag embeds extraction and validate ambiguous embeds'
URLs (#9163, #12005, #12178, #12480)
+ [udemy] Add support for react rendition (#12744)
version 2017.04.15 version 2017.04.15
Extractors Extractors

2
Makefile
View File

@ -1,7 +1,7 @@
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean: clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete find . -name "*.pyc" -delete
find . -name "*.class" -delete find . -name "*.class" -delete

3
README.md
View File

@ -187,6 +187,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
and ISM) and ISM)
--abort-on-unavailable-fragment Abort downloading when some fragment is not --abort-on-unavailable-fragment Abort downloading when some fragment is not
available available
--keep-fragments Keep downloaded fragments on disk after
downloading is finished; fragments are
erased by default
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K) --buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
(default is 1024) (default is 1024)
--no-resize-buffer Do not automatically adjust the buffer --no-resize-buffer Do not automatically adjust the buffer

7
docs/supportedsites.md
View File

@ -45,6 +45,7 @@
- **anderetijden**: npo.nl and ntr.nl - **anderetijden**: npo.nl and ntr.nl
- **AnimeOnDemand** - **AnimeOnDemand**
- **anitube.se** - **anitube.se**
- **Anvato**
- **AnySex** - **AnySex**
- **Aparat** - **Aparat**
- **AppleConnect** - **AppleConnect**
@ -81,8 +82,6 @@
- **AZMedien**: AZ Medien videos - **AZMedien**: AZ Medien videos
- **AZMedienPlaylist**: AZ Medien playlists - **AZMedienPlaylist**: AZ Medien playlists
- **AZMedienShowPlaylist**: AZ Medien show playlists - **AZMedienShowPlaylist**: AZ Medien show playlists
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频 - **BaiduVideo**: 百度视频
- **bambuser** - **bambuser**
- **bambuser:channel** - **bambuser:channel**
@ -531,6 +530,7 @@
- **NJPWWorld**: 新日本プロレスワールド - **NJPWWorld**: 新日本プロレスワールド
- **NobelPrize** - **NobelPrize**
- **Noco** - **Noco**
- **Noovo**
- **Normalboots** - **Normalboots**
- **NosVideo** - **NosVideo**
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
@ -745,6 +745,7 @@
- **Steam** - **Steam**
- **Stitcher** - **Stitcher**
- **Streamable** - **Streamable**
- **Streamango**
- **streamcloud.eu** - **streamcloud.eu**
- **StreamCZ** - **StreamCZ**
- **StreetVoice** - **StreetVoice**
@ -966,6 +967,7 @@
- **wrzuta.pl** - **wrzuta.pl**
- **wrzuta.pl:playlist** - **wrzuta.pl:playlist**
- **WSJ**: Wall Street Journal - **WSJ**: Wall Street Journal
- **WSJArticle**
- **XBef** - **XBef**
- **XboxClips** - **XboxClips**
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo
@ -1013,6 +1015,7 @@
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication) - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks** - **Zapiks**
- **Zaq1**
- **ZDF** - **ZDF**
- **ZDFChannel** - **ZDFChannel**
- **zingmp3**: mp3.zing.vn - **zingmp3**: mp3.zing.vn

315
test/test_InfoExtractor.py
View File

@ -3,12 +3,13 @@
from __future__ import unicode_literals from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import io
import os import os
import sys import sys
import unittest import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, expect_dict from test.helper import FakeYDL, expect_dict, expect_value
from youtube_dl.extractor.common import InfoExtractor from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
@ -175,6 +176,318 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
}] }]
}) })
def test_parse_m3u8_formats(self):
_TEST_CASES = [
(
# https://github.com/rg3/youtube-dl/issues/11507
# http://pluzz.francetv.fr/videos/le_ministere.html
'pluzz_francetv_11507',
'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
[{
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '180',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 180,
'width': 256,
'height': 144,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '303',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 303,
'width': 320,
'height': 180,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '575',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 575,
'width': 512,
'height': 288,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '831',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.77.30',
'tbr': 831,
'width': 704,
'height': 396,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'protocol': 'm3u8',
'format_id': '1467',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.77.30',
'tbr': 1467,
'width': 1024,
'height': 576,
}]
),
(
# https://github.com/rg3/youtube-dl/issues/11995
# http://teamcoco.com/video/clueless-gamer-super-bowl-for-honor
'teamcoco_11995',
'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
[{
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': 'audio-0-Default',
'protocol': 'm3u8',
'vcodec': 'none',
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': 'audio-1-Default',
'protocol': 'm3u8',
'vcodec': 'none',
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '71',
'protocol': 'm3u8',
'acodec': 'mp4a.40.5',
'vcodec': 'none',
'tbr': 71,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '413',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.42001e',
'tbr': 413,
'width': 400,
'height': 224,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '522',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.42001e',
'tbr': 522,
'width': 400,
'height': 224,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-1m_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '1205',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.4d001e',
'tbr': 1205,
'width': 640,
'height': 360,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-2m_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '2374',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.4d001f',
'tbr': 2374,
'width': 1024,
'height': 576,
}]
),
(
# https://github.com/rg3/youtube-dl/issues/12211
# http://video.toggle.sg/en/series/whoopie-s-world/ep3/478601
'toggle_mobile_12211',
'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
[{
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': 'audio-English',
'protocol': 'm3u8',
'language': 'eng',
'vcodec': 'none',
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': 'audio-Undefined',
'protocol': 'm3u8',
'language': 'und',
'vcodec': 'none',
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '155',
'protocol': 'm3u8',
'tbr': 155.648,
'width': 320,
'height': 180,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '502',
'protocol': 'm3u8',
'tbr': 502.784,
'width': 480,
'height': 270,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '827',
'protocol': 'm3u8',
'tbr': 827.392,
'width': 640,
'height': 360,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '1396',
'protocol': 'm3u8',
'tbr': 1396.736,
'width': 854,
'height': 480,
}]
),
(
# http://www.twitch.tv/riotgames/v/6528877
'twitch_vod',
'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
[{
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Audio Only',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'none',
'tbr': 182.725,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Mobile',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C00D',
'tbr': 280.474,
'width': 400,
'height': 226,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Low',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01E',
'tbr': 628.347,
'width': 640,
'height': 360,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Medium',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01E',
'tbr': 893.387,
'width': 852,
'height': 480,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'High',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01F',
'tbr': 1603.789,
'width': 1280,
'height': 720,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Source',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.100.31',
'tbr': 3214.134,
'width': 1280,
'height': 720,
}]
),
(
# http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
# EXT-X-STREAM-INF tag with NAME attribute that is not defined
# in HLS specification
'vidio',
'https://www.vidio.com/videos/165683/playlist.m3u8',
[{
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '270p 3G',
'protocol': 'm3u8',
'tbr': 300,
'width': 480,
'height': 270,
}, {
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '360p SD',
'protocol': 'm3u8',
'tbr': 600,
'width': 640,
'height': 360,
}, {
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '720p HD',
'protocol': 'm3u8',
'tbr': 1200,
'width': 1280,
'height': 720,
}]
)
]
for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:
with io.open('./test/testdata/m3u8/%s.m3u8' % m3u8_file,
mode='r', encoding='utf-8') as f:
formats = self.ie._parse_m3u8_formats(
f.read(), m3u8_url, ext='mp4')
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

4
test/test_YoutubeDL.py
View File

@ -755,6 +755,7 @@ class TestYoutubeDL(unittest.TestCase):
'_type': 'url_transparent', '_type': 'url_transparent',
'url': 'foo2:', 'url': 'foo2:',
'ie_key': 'Foo2', 'ie_key': 'Foo2',
'title': 'foo1 title'
} }
class Foo2IE(InfoExtractor): class Foo2IE(InfoExtractor):
@ -771,7 +772,7 @@ class TestYoutubeDL(unittest.TestCase):
_VALID_URL = r'foo3:' _VALID_URL = r'foo3:'
def _real_extract(self, url): def _real_extract(self, url):
return _make_result([{'url': TEST_URL}]) return _make_result([{'url': TEST_URL}], title='foo3 title')
ydl.add_info_extractor(Foo1IE(ydl)) ydl.add_info_extractor(Foo1IE(ydl))
ydl.add_info_extractor(Foo2IE(ydl)) ydl.add_info_extractor(Foo2IE(ydl))
@ -779,6 +780,7 @@ class TestYoutubeDL(unittest.TestCase):
ydl.extract_info('foo1:') ydl.extract_info('foo1:')
downloaded = ydl.downloaded_info_dicts[0] downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['url'], TEST_URL) self.assertEqual(downloaded['url'], TEST_URL)
self.assertEqual(downloaded['title'], 'foo1 title')
if __name__ == '__main__': if __name__ == '__main__':

2
test/test_download.py
View File

@ -225,7 +225,7 @@ def generator(test_case, tname):
format_bytes(got_fsize))) format_bytes(got_fsize)))
if 'md5' in tc: if 'md5' in tc:
md5_for_file = _file_md5(tc_filename) md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5']) self.assertEqual(tc['md5'], md5_for_file)
# Finally, check test cases' data again but this time against # Finally, check test cases' data again but this time against
# extracted data from info JSON file written during processing # extracted data from info JSON file written during processing
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json' info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'

54
test/test_utils.py
View File

@ -44,6 +44,7 @@ from youtube_dl.utils import (
limit_length, limit_length,
mimetype2ext, mimetype2ext,
month_by_name, month_by_name,
multipart_encode,
ohdave_rsa_encrypt, ohdave_rsa_encrypt,
OnDemandPagedList, OnDemandPagedList,
orderedSet, orderedSet,
@ -338,6 +339,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None) self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500) self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100) self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
def test_determine_ext(self): def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4') self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@ -619,6 +621,16 @@ class TestUtil(unittest.TestCase):
'http://example.com/path', {'test': '第二行тест'})), 'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82')) query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_multipart_encode(self):
self.assertEqual(
multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
self.assertEqual(
multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
self.assertRaises(
ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
def test_dict_get(self): def test_dict_get(self):
FALSE_VALUES = { FALSE_VALUES = {
'none': None, 'none': None,
@ -899,6 +911,7 @@ class TestUtil(unittest.TestCase):
def test_clean_html(self): def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b') self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"') self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self): def test_intlist_to_bytes(self):
self.assertEqual( self.assertEqual(
@ -1069,6 +1082,47 @@ The first line
''' '''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data) self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
<tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
<head>
<styling>
<style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
<style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
<style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
<style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
</styling>
</head>
<body tts:textAlign="center" style="s0">
<div>
<p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
<p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
<p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
<p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:02,080 --> 00:00:05,839
<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
2
00:00:02,080 --> 00:00:05,839
<b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
</font>part 2</font></b>
3
00:00:05,839 --> 00:00:09,560
<u><font color="lime">line 3
part 3</font></u>
4
00:00:09,560 --> 00:00:12,359
<i><u><font color="yellow"><font color="lime">inner
</font>style</font></u></i>
'''
self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
def test_cli_option(self): def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128']) self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), []) self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])

14
test/testdata/m3u8/pluzz_francetv_11507.m3u8 vendored Normal file
View File

@ -0,0 +1,14 @@
#EXTM3U
#EXT-X-VERSION:5
#EXT-X-MEDIA:TYPE=SUBTITLES,GROUP-ID="subs",NAME="Francais",DEFAULT=NO,FORCED=NO,URI="http://replayftv-pmd.francetv.fr/subtitles/2017/16/156589847-1492488987.m3u8",LANGUAGE="fra"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="aac",LANGUAGE="fra",NAME="Francais",DEFAULT=YES, AUTOSELECT=YES
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=180000,RESOLUTION=256x144,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=303000,RESOLUTION=320x180,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=575000,RESOLUTION=512x288,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=831000,RESOLUTION=704x396,CODECS="avc1.77.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=1467000,RESOLUTION=1024x576,CODECS="avc1.77.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0

16
test/testdata/m3u8/teamcoco_11995.m3u8 vendored Normal file
View File

@ -0,0 +1,16 @@
#EXTM3U
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-0",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-1",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=37862000,CODECS="avc1.4d001f",URI="hls/CONAN_020217_Highlight_show-2m_iframe.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=18750000,CODECS="avc1.4d001e",URI="hls/CONAN_020217_Highlight_show-1m_iframe.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=6535000,CODECS="avc1.42001e",URI="hls/CONAN_020217_Highlight_show-400k_iframe.m3u8"
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=2374000,RESOLUTION=1024x576,CODECS="avc1.4d001f,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-2m_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1205000,RESOLUTION=640x360,CODECS="avc1.4d001e,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-1m_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=522000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-400k_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=413000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.5",AUDIO="audio-1"
hls/CONAN_020217_Highlight_show-400k_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=71000,CODECS="mp4a.40.5",AUDIO="audio-1"
hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8

13
test/testdata/m3u8/toggle_mobile_12211.m3u8 vendored Normal file
View File

@ -0,0 +1,13 @@
#EXTM3U
#EXT-X-VERSION:4
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="eng",NAME="English",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="und",NAME="Undefined",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8"
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=155648,RESOLUTION=320x180,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=502784,RESOLUTION=480x270,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=827392,RESOLUTION=640x360,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1396736,RESOLUTION=854x480,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8

20
test/testdata/m3u8/twitch_vod.m3u8 vendored Normal file
View File

@ -0,0 +1,20 @@
#EXTM3U
#EXT-X-TWITCH-INFO:ORIGIN="s3",CLUSTER="edgecast_vod",REGION="EU",MANIFEST-CLUSTER="edgecast_vod",USER-IP="109.171.17.81"
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="chunked",NAME="Source",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=3214134,CODECS="avc1.100.31,mp4a.40.2",RESOLUTION="1280x720",VIDEO="chunked"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="high",NAME="High",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1603789,CODECS="avc1.42C01F,mp4a.40.2",RESOLUTION="1280x720",VIDEO="high"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="medium",NAME="Medium",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=893387,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="852x480",VIDEO="medium"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="low",NAME="Low",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=628347,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="640x360",VIDEO="low"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="mobile",NAME="Mobile",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=280474,CODECS="avc1.42C00D,mp4a.40.2",RESOLUTION="400x226",VIDEO="mobile"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="audio_only",NAME="Audio Only",AUTOSELECT=NO,DEFAULT=NO
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=182725,CODECS="mp4a.40.2",VIDEO="audio_only"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8

10
test/testdata/m3u8/vidio.m3u8 vendored Normal file
View File

@ -0,0 +1,10 @@
#EXTM3U
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=300000,RESOLUTION=480x270,NAME="270p 3G"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=600000,RESOLUTION=640x360,NAME="360p SD"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1200000,RESOLUTION=1280x720,NAME="720p HD"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8

14
youtube_dl/YoutubeDL.py
View File

@ -640,7 +640,7 @@ class YoutubeDL(object):
NUMERIC_FIELDS = set(( NUMERIC_FIELDS = set((
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx', 'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'upload_year', 'upload_month', 'upload_day', 'timestamp', 'upload_year', 'upload_month', 'upload_day',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count', 'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'average_rating', 'comment_count', 'age_limit', 'average_rating', 'comment_count', 'age_limit',
'start_time', 'end_time', 'start_time', 'end_time',
@ -672,8 +672,7 @@ class YoutubeDL(object):
FORMAT_RE.format(numeric_field), FORMAT_RE.format(numeric_field),
r'%({0})s'.format(numeric_field), outtmpl) r'%({0})s'.format(numeric_field), outtmpl)
tmpl = expand_path(outtmpl) filename = expand_path(outtmpl % template_dict)
filename = tmpl % template_dict
# Temporary fix for #4787 # Temporary fix for #4787
# 'Treat' all problem characters by passing filename through preferredencoding # 'Treat' all problem characters by passing filename through preferredencoding
# to workaround encoding issues with subprocess on python2 @ Windows # to workaround encoding issues with subprocess on python2 @ Windows
@ -851,7 +850,14 @@ class YoutubeDL(object):
new_result = info.copy() new_result = info.copy()
new_result.update(force_properties) new_result.update(force_properties)
assert new_result.get('_type') != 'url_transparent' # Extracted info may not be a video result (i.e.
# info.get('_type', 'video') != video) but rather an url or
# url_transparent. In such cases outer metadata (from ie_result)
# should be propagated to inner one (info). For this to happen
# _type of info should be overridden with url_transparent. This
# fixes issue from https://github.com/rg3/youtube-dl/pull/11163.
if new_result.get('_type') == 'url':
new_result['_type'] = 'url_transparent'
return self.process_ie_result( return self.process_ie_result(
new_result, download=download, extra_info=extra_info) new_result, download=download, extra_info=extra_info)

1
youtube_dl/__init__.py
View File

@ -343,6 +343,7 @@ def _real_main(argv=None):
'retries': opts.retries, 'retries': opts.retries,
'fragment_retries': opts.fragment_retries, 'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments, 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'keep_fragments': opts.keep_fragments,
'buffersize': opts.buffersize, 'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer, 'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl, 'continuedl': opts.continue_dl,

32
youtube_dl/downloader/common.py
View File

@ -187,6 +187,9 @@ class FileDownloader(object):
return filename[:-len('.part')] return filename[:-len('.part')]
return filename return filename
def ytdl_filename(self, filename):
return filename + '.ytdl'
def try_rename(self, old_filename, new_filename): def try_rename(self, old_filename, new_filename):
try: try:
if old_filename == new_filename: if old_filename == new_filename:
@ -327,21 +330,22 @@ class FileDownloader(object):
os.path.exists(encodeFilename(filename)) os.path.exists(encodeFilename(filename))
) )
continuedl_and_exists = ( if not hasattr(filename, 'write'):
self.params.get('continuedl', True) and continuedl_and_exists = (
os.path.isfile(encodeFilename(filename)) and self.params.get('continuedl', True) and
not self.params.get('nopart', False) os.path.isfile(encodeFilename(filename)) and
) not self.params.get('nopart', False)
)
# Check file already present # Check file already present
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists): if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename) self.report_file_already_downloaded(filename)
self._hook_progress({ self._hook_progress({
'filename': filename, 'filename': filename,
'status': 'finished', 'status': 'finished',
'total_bytes': os.path.getsize(encodeFilename(filename)), 'total_bytes': os.path.getsize(encodeFilename(filename)),
}) })
return True return True
min_sleep_interval = self.params.get('sleep_interval') min_sleep_interval = self.params.get('sleep_interval')
if min_sleep_interval: if min_sleep_interval:

43
youtube_dl/downloader/dash.py
View File

@ -1,13 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os
from .fragment import FragmentFD from .fragment import FragmentFD
from ..compat import compat_urllib_error from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
class DashSegmentsFD(FragmentFD): class DashSegmentsFD(FragmentFD):
@ -28,31 +22,24 @@ class DashSegmentsFD(FragmentFD):
self._prepare_and_start_frag_download(ctx) self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0) fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True) skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
def process_segment(segment, tmp_filename, num): frag_index = 0
segment_url = segment['url'] for i, segment in enumerate(segments):
segment_name = 'Frag%d' % num frag_index += 1
target_filename = '%s-%s' % (tmp_filename, segment_name) if frag_index <= ctx['fragment_index']:
continue
# In DASH, the first segment contains necessary headers to # In DASH, the first segment contains necessary headers to
# generate a valid MP4 file, so always abort for the first segment # generate a valid MP4 file, so always abort for the first segment
fatal = num == 0 or not skip_unavailable_fragments fatal = i == 0 or not skip_unavailable_fragments
count = 0 count = 0
while count <= fragment_retries: while count <= fragment_retries:
try: try:
success = ctx['dl'].download(target_filename, { success, frag_content = self._download_fragment(ctx, segment['url'], info_dict)
'url': segment_url,
'http_headers': info_dict.get('http_headers'),
})
if not success: if not success:
return False return False
down, target_sanitized = sanitize_open(target_filename, 'rb') self._append_fragment(ctx, frag_content)
ctx['dest_stream'].write(down.read())
down.close()
segments_filenames.append(target_sanitized)
break break
except compat_urllib_error.HTTPError as err: except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the # YouTube may often return 404 HTTP error for a fragment causing the
@ -63,22 +50,14 @@ class DashSegmentsFD(FragmentFD):
# HTTP error. # HTTP error.
count += 1 count += 1
if count <= fragment_retries: if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries) self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries: if count > fragment_retries:
if not fatal: if not fatal:
self.report_skip_fragment(segment_name) self.report_skip_fragment(frag_index)
return True continue
self.report_error('giving up after %s fragment retries' % fragment_retries) self.report_error('giving up after %s fragment retries' % fragment_retries)
return False return False
return True
for i, segment in enumerate(segments):
if not process_segment(segment, ctx['tmpfilename'], i):
return False
self._finish_frag_download(ctx) self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True return True

12
youtube_dl/downloader/external.py
View File

@ -29,7 +29,17 @@ class ExternalFD(FileDownloader):
self.report_destination(filename) self.report_destination(filename)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
retval = self._call_downloader(tmpfilename, info_dict) try:
retval = self._call_downloader(tmpfilename, info_dict)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
raise
# Live stream downloading cancellation should be considered as
# correct and expected termination thus all postprocessing
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
if retval == 0: if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename)) fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize)) self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))

33
youtube_dl/downloader/f4m.py
View File

@ -3,7 +3,6 @@ from __future__ import division, unicode_literals
import base64 import base64
import io import io
import itertools import itertools
import os
import time import time
from .fragment import FragmentFD from .fragment import FragmentFD
@ -16,9 +15,7 @@ from ..compat import (
compat_struct_unpack, compat_struct_unpack,
) )
from ..utils import ( from ..utils import (
encodeFilename,
fix_xml_ampersands, fix_xml_ampersands,
sanitize_open,
xpath_text, xpath_text,
) )
@ -366,17 +363,21 @@ class F4mFD(FragmentFD):
dest_stream = ctx['dest_stream'] dest_stream = ctx['dest_stream']
write_flv_header(dest_stream) if ctx['complete_frags_downloaded_bytes'] == 0:
if not live: write_flv_header(dest_stream)
write_metadata_tag(dest_stream, metadata) if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url) base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx) self._start_frag_download(ctx)
frags_filenames = [] frag_index = 0
while fragments_list: while fragments_list:
seg_i, frag_i = fragments_list.pop(0) seg_i, frag_i = fragments_list.pop(0)
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
name = 'Seg%d-Frag%d' % (seg_i, frag_i) name = 'Seg%d-Frag%d' % (seg_i, frag_i)
query = [] query = []
if base_url_parsed.query: if base_url_parsed.query:
@ -386,17 +387,10 @@ class F4mFD(FragmentFD):
if info_dict.get('extra_param_to_segment_url'): if info_dict.get('extra_param_to_segment_url'):
query.append(info_dict['extra_param_to_segment_url']) query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query)) url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try: try:
success = ctx['dl'].download(frag_filename, { success, down_data = self._download_fragment(ctx, url_parsed.geturl(), info_dict)
'url': url_parsed.geturl(),
'http_headers': info_dict.get('http_headers'),
})
if not success: if not success:
return False return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
down_data = down.read()
down.close()
reader = FlvReader(down_data) reader = FlvReader(down_data)
while True: while True:
try: try:
@ -411,12 +405,8 @@ class F4mFD(FragmentFD):
break break
raise raise
if box_type == b'mdat': if box_type == b'mdat':
dest_stream.write(box_data) self._append_fragment(ctx, box_data)
break break
if live:
os.remove(encodeFilename(frag_sanitized))
else:
frags_filenames.append(frag_sanitized)
except (compat_urllib_error.HTTPError, ) as err: except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410): if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue # We didn't keep up with the live window. Continue
@ -436,7 +426,4 @@ class F4mFD(FragmentFD):
self._finish_frag_download(ctx) self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True return True

122
youtube_dl/downloader/fragment.py
View File

@ -2,6 +2,7 @@ from __future__ import division, unicode_literals
import os import os
import time import time
import json
from .common import FileDownloader from .common import FileDownloader
from .http import HttpFD from .http import HttpFD
@ -28,15 +29,37 @@ class FragmentFD(FileDownloader):
and hlsnative only) and hlsnative only)
skip_unavailable_fragments: skip_unavailable_fragments:
Skip unavailable fragments (DASH and hlsnative only) Skip unavailable fragments (DASH and hlsnative only)
keep_fragments: Keep downloaded fragments on disk after downloading is
finished
For each incomplete fragment download youtube-dl keeps on disk a special
bookkeeping file with download state and metadata (in future such files will
be used for any incomplete download handled by youtube-dl). This file is
used to properly handle resuming, check download file consistency and detect
potential errors. The file has a .ytdl extension and represents a standard
JSON file of the following format:
extractor:
Dictionary of extractor related data. TBD.
downloader:
Dictionary of downloader related data. May contain following data:
current_fragment:
Dictionary with current (being downloaded) fragment data:
index: 0-based index of current fragment among all fragments
fragment_count:
Total count of fragments
This feature is experimental and file format may change in future.
""" """
def report_retry_fragment(self, err, fragment_name, count, retries): def report_retry_fragment(self, err, frag_index, count, retries):
self.to_screen( self.to_screen(
'[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...' '[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s)...'
% (error_to_compat_str(err), fragment_name, count, self.format_retries(retries))) % (error_to_compat_str(err), frag_index, count, self.format_retries(retries)))
def report_skip_fragment(self, fragment_name): def report_skip_fragment(self, frag_index):
self.to_screen('[download] Skipping fragment %s...' % fragment_name) self.to_screen('[download] Skipping fragment %d...' % frag_index)
def _prepare_url(self, info_dict, url): def _prepare_url(self, info_dict, url):
headers = info_dict.get('http_headers') headers = info_dict.get('http_headers')
@ -46,6 +69,51 @@ class FragmentFD(FileDownloader):
self._prepare_frag_download(ctx) self._prepare_frag_download(ctx)
self._start_frag_download(ctx) self._start_frag_download(ctx)
@staticmethod
def __do_ytdl_file(ctx):
return not ctx['live'] and not ctx['tmpfilename'] == '-'
def _read_ytdl_file(self, ctx):
stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'r')
ctx['fragment_index'] = json.loads(stream.read())['downloader']['current_fragment']['index']
stream.close()
def _write_ytdl_file(self, ctx):
frag_index_stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'w')
downloader = {
'current_fragment': {
'index': ctx['fragment_index'],
},
}
if ctx.get('fragment_count') is not None:
downloader['fragment_count'] = ctx['fragment_count']
frag_index_stream.write(json.dumps({'downloader': downloader}))
frag_index_stream.close()
def _download_fragment(self, ctx, frag_url, info_dict, headers=None):
fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
success = ctx['dl'].download(fragment_filename, {
'url': frag_url,
'http_headers': headers or info_dict.get('http_headers'),
})
if not success:
return False, None
down, frag_sanitized = sanitize_open(fragment_filename, 'rb')
ctx['fragment_filename_sanitized'] = frag_sanitized
frag_content = down.read()
down.close()
return True, frag_content
def _append_fragment(self, ctx, frag_content):
try:
ctx['dest_stream'].write(frag_content)
finally:
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
os.remove(ctx['fragment_filename_sanitized'])
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx): def _prepare_frag_download(self, ctx):
if 'live' not in ctx: if 'live' not in ctx:
ctx['live'] = False ctx['live'] = False
@ -66,11 +134,36 @@ class FragmentFD(FileDownloader):
} }
) )
tmpfilename = self.temp_name(ctx['filename']) tmpfilename = self.temp_name(ctx['filename'])
dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb') open_mode = 'wb'
resume_len = 0
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
open_mode = 'ab'
resume_len = os.path.getsize(encodeFilename(tmpfilename))
# Should be initialized before ytdl file check
ctx.update({
'tmpfilename': tmpfilename,
'fragment_index': 0,
})
if self.__do_ytdl_file(ctx):
if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
self._read_ytdl_file(ctx)
else:
self._write_ytdl_file(ctx)
if ctx['fragment_index'] > 0:
assert resume_len > 0
dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode)
ctx.update({ ctx.update({
'dl': dl, 'dl': dl,
'dest_stream': dest_stream, 'dest_stream': dest_stream,
'tmpfilename': tmpfilename, 'tmpfilename': tmpfilename,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': resume_len,
}) })
def _start_frag_download(self, ctx): def _start_frag_download(self, ctx):
@ -79,9 +172,9 @@ class FragmentFD(FileDownloader):
# hook # hook
state = { state = {
'status': 'downloading', 'status': 'downloading',
'downloaded_bytes': 0, 'downloaded_bytes': ctx['complete_frags_downloaded_bytes'],
'frag_index': 0, 'fragment_index': ctx['fragment_index'],
'frag_count': total_frags, 'fragment_count': total_frags,
'filename': ctx['filename'], 'filename': ctx['filename'],
'tmpfilename': ctx['tmpfilename'], 'tmpfilename': ctx['tmpfilename'],
} }
@ -89,8 +182,6 @@ class FragmentFD(FileDownloader):
start = time.time() start = time.time()
ctx.update({ ctx.update({
'started': start, 'started': start,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': 0,
# Amount of fragment's bytes downloaded by the time of the previous # Amount of fragment's bytes downloaded by the time of the previous
# frag progress hook invocation # frag progress hook invocation
'prev_frag_downloaded_bytes': 0, 'prev_frag_downloaded_bytes': 0,
@ -106,11 +197,12 @@ class FragmentFD(FileDownloader):
if not ctx['live']: if not ctx['live']:
estimated_size = ( estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) / (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags) (state['fragment_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished': if s['status'] == 'finished':
state['frag_index'] += 1 state['fragment_index'] += 1
ctx['fragment_index'] = state['fragment_index']
state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes'] state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes'] ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
ctx['prev_frag_downloaded_bytes'] = 0 ctx['prev_frag_downloaded_bytes'] = 0
@ -132,6 +224,10 @@ class FragmentFD(FileDownloader):
def _finish_frag_download(self, ctx): def _finish_frag_download(self, ctx):
ctx['dest_stream'].close() ctx['dest_stream'].close()
if self.__do_ytdl_file(ctx):
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
if os.path.isfile(ytdl_filename):
os.remove(ytdl_filename)
elapsed = time.time() - ctx['started'] elapsed = time.time() - ctx['started']
self.try_rename(ctx['tmpfilename'], ctx['filename']) self.try_rename(ctx['tmpfilename'], ctx['filename'])
fsize = os.path.getsize(encodeFilename(ctx['filename'])) fsize = os.path.getsize(encodeFilename(ctx['filename']))

34
youtube_dl/downloader/hls.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os.path
import re import re
import binascii import binascii
try: try:
@ -18,8 +17,6 @@ from ..compat import (
compat_struct_pack, compat_struct_pack,
) )
from ..utils import ( from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes, parse_m3u8_attributes,
update_url_query, update_url_query,
) )
@ -103,17 +100,18 @@ class HlsFD(FragmentFD):
media_sequence = 0 media_sequence = 0
decrypt_info = {'METHOD': 'NONE'} decrypt_info = {'METHOD': 'NONE'}
byte_range = {} byte_range = {}
frags_filenames = [] frag_index = 0
for line in s.splitlines(): for line in s.splitlines():
line = line.strip() line = line.strip()
if line: if line:
if not line.startswith('#'): if not line.startswith('#'):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
frag_url = ( frag_url = (
line line
if re.match(r'^https?://', line) if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line)) else compat_urlparse.urljoin(man_url, line))
frag_name = 'Frag%d' % i
frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
if extra_query: if extra_query:
frag_url = update_url_query(frag_url, extra_query) frag_url = update_url_query(frag_url, extra_query)
count = 0 count = 0
@ -122,15 +120,10 @@ class HlsFD(FragmentFD):
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end']) headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'])
while count <= fragment_retries: while count <= fragment_retries:
try: try:
success = ctx['dl'].download(frag_filename, { success, frag_content = self._download_fragment(
'url': frag_url, ctx, frag_url, info_dict, headers)
'http_headers': headers,
})
if not success: if not success:
return False return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
break break
except compat_urllib_error.HTTPError as err: except compat_urllib_error.HTTPError as err:
# Unavailable (possibly temporary) fragments may be served. # Unavailable (possibly temporary) fragments may be served.
@ -139,28 +132,29 @@ class HlsFD(FragmentFD):
# https://github.com/rg3/youtube-dl/issues/10448). # https://github.com/rg3/youtube-dl/issues/10448).
count += 1 count += 1
if count <= fragment_retries: if count <= fragment_retries:
self.report_retry_fragment(err, frag_name, count, fragment_retries) self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries: if count > fragment_retries:
if skip_unavailable_fragments: if skip_unavailable_fragments:
i += 1 i += 1
media_sequence += 1 media_sequence += 1
self.report_skip_fragment(frag_name) self.report_skip_fragment(frag_index)
continue continue
self.report_error( self.report_error(
'giving up after %s fragment retries' % fragment_retries) 'giving up after %s fragment retries' % fragment_retries)
return False return False
if decrypt_info['METHOD'] == 'AES-128': if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(decrypt_info['URI']).read()
frag_content = AES.new( frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
ctx['dest_stream'].write(frag_content) self._append_fragment(ctx, frag_content)
frags_filenames.append(frag_sanitized)
# We only download the first fragment during the test # We only download the first fragment during the test
if test: if test:
break break
i += 1 i += 1
media_sequence += 1 media_sequence += 1
elif line.startswith('#EXT-X-KEY'): elif line.startswith('#EXT-X-KEY'):
decrypt_url = decrypt_info.get('URI')
decrypt_info = parse_m3u8_attributes(line[11:]) decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128': if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info: if 'IV' in decrypt_info:
@ -170,7 +164,8 @@ class HlsFD(FragmentFD):
man_url, decrypt_info['URI']) man_url, decrypt_info['URI'])
if extra_query: if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query) decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read() if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'): elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:]) media_sequence = int(line[22:])
elif line.startswith('#EXT-X-BYTERANGE'): elif line.startswith('#EXT-X-BYTERANGE'):
@ -183,7 +178,4 @@ class HlsFD(FragmentFD):
self._finish_frag_download(ctx) self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True return True

34
youtube_dl/downloader/ism.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os
import time import time
import struct import struct
import binascii import binascii
@ -8,10 +7,6 @@ import io
from .fragment import FragmentFD from .fragment import FragmentFD
from ..compat import compat_urllib_error from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
u8 = struct.Struct(b'>B') u8 = struct.Struct(b'>B')
@ -225,50 +220,39 @@ class IsmFD(FragmentFD):
self._prepare_and_start_frag_download(ctx) self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0) fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True) skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
track_written = False track_written = False
frag_index = 0
for i, segment in enumerate(segments): for i, segment in enumerate(segments):
segment_url = segment['url'] frag_index += 1
segment_name = 'Frag%d' % i if frag_index <= ctx['fragment_index']:
target_filename = '%s-%s' % (ctx['tmpfilename'], segment_name) continue
count = 0 count = 0
while count <= fragment_retries: while count <= fragment_retries:
try: try:
success = ctx['dl'].download(target_filename, { success, frag_content = self._download_fragment(ctx, segment['url'], info_dict)
'url': segment_url,
'http_headers': info_dict.get('http_headers'),
})
if not success: if not success:
return False return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
down_data = down.read()
if not track_written: if not track_written:
tfhd_data = extract_box_data(down_data, [b'moof', b'traf', b'tfhd']) tfhd_data = extract_box_data(frag_content, [b'moof', b'traf', b'tfhd'])
info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0] info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0]
write_piff_header(ctx['dest_stream'], info_dict['_download_params']) write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
track_written = True track_written = True
ctx['dest_stream'].write(down_data) self._append_fragment(ctx, frag_content)
down.close()
segments_filenames.append(target_sanitized)
break break
except compat_urllib_error.HTTPError as err: except compat_urllib_error.HTTPError as err:
count += 1 count += 1
if count <= fragment_retries: if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries) self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries: if count > fragment_retries:
if skip_unavailable_fragments: if skip_unavailable_fragments:
self.report_skip_fragment(segment_name) self.report_skip_fragment(frag_index)
continue continue
self.report_error('giving up after %s fragment retries' % fragment_retries) self.report_error('giving up after %s fragment retries' % fragment_retries)
return False return False
self._finish_frag_download(ctx) self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True return True

6
youtube_dl/extractor/adobepass.py
View File

@ -1308,6 +1308,12 @@ class AdobePassIE(InfoExtractor):
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0' _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MVPD_CACHE = 'ap-mvpd' _MVPD_CACHE = 'ap-mvpd'
def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {})
headers.update(self.geo_verification_headers())
kwargs['headers'] = headers
return super(AdobePassIE, self)._download_webpage_handle(*args, **kwargs)
@staticmethod @staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating): def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel') channel = etree.Element('channel')

14
youtube_dl/extractor/aenetworks.py
View File

@ -101,10 +101,14 @@ class AENetworksIE(AENetworksBaseIE):
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage): for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result( entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks')) compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
return self.playlist_result( if entries:
entries, self._html_search_meta('aetn:SeriesId', webpage), return self.playlist_result(
self._html_search_meta('aetn:SeriesTitle', webpage)) entries, self._html_search_meta('aetn:SeriesId', webpage),
elif url_parts_len == 2: self._html_search_meta('aetn:SeriesTitle', webpage))
else:
# single season
url_parts_len = 2
if url_parts_len == 2:
entries = [] entries = []
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage): for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item) episode_attributes = extract_attributes(episode_item)
@ -112,7 +116,7 @@ class AENetworksIE(AENetworksBaseIE):
url, episode_attributes['data-canonical']) url, episode_attributes['data-canonical'])
entries.append(self.url_result( entries.append(self.url_result(
episode_url, 'AENetworks', episode_url, 'AENetworks',
episode_attributes['data-videoid'])) episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
return self.playlist_result( return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage)) entries, self._html_search_meta('aetn:SeasonId', webpage))

3
youtube_dl/extractor/afreecatv.py
View File

@ -207,11 +207,10 @@ class AfreecaTVIE(InfoExtractor):
file_url, video_id, 'mp4', entry_protocol='m3u8_native', file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num) note='Downloading part %d m3u8 information' % file_num)
title = title if one else '%s (part %d)' % (title, file_num)
file_info = common_entry.copy() file_info = common_entry.copy()
file_info.update({ file_info.update({
'id': format_id, 'id': format_id,
'title': title, 'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date, 'upload_date': upload_date,
'duration': file_duration, 'duration': file_duration,
'formats': formats, 'formats': formats,

26
youtube_dl/extractor/amp.py
View File

@ -7,15 +7,19 @@ from ..utils import (
parse_iso8601, parse_iso8601,
mimetype2ext, mimetype2ext,
determine_ext, determine_ext,
ExtractorError,
) )
class AMPIE(InfoExtractor): class AMPIE(InfoExtractor):
# parse Akamai Adaptive Media Player feed # parse Akamai Adaptive Media Player feed
def _extract_feed_info(self, url): def _extract_feed_info(self, url):
item = self._download_json( feed = self._download_json(
url, None, 'Downloading Akamai AMP feed', url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')['channel']['item'] 'Unable to download Akamai AMP feed')
item = feed.get('channel', {}).get('item')
if not item:
raise ExtractorError('%s said: %s' % (self.IE_NAME, feed['error']))
video_id = item['guid'] video_id = item['guid']
@ -30,9 +34,12 @@ class AMPIE(InfoExtractor):
if isinstance(media_thumbnail, dict): if isinstance(media_thumbnail, dict):
media_thumbnail = [media_thumbnail] media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail: for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data['@attributes'] thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({ thumbnails.append({
'url': self._proto_relative_url(thumbnail['url'], 'http:'), 'url': self._proto_relative_url(thumbnail_url, 'http:'),
'width': int_or_none(thumbnail.get('width')), 'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')), 'height': int_or_none(thumbnail.get('height')),
}) })
@ -43,9 +50,14 @@ class AMPIE(InfoExtractor):
if isinstance(media_subtitle, dict): if isinstance(media_subtitle, dict):
media_subtitle = [media_subtitle] media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle: for subtitle_data in media_subtitle:
subtitle = subtitle_data['@attributes'] subtitle = subtitle_data.get('@attributes', {})
lang = subtitle.get('lang') or 'en' subtitle_href = subtitle.get('href')
subtitles[lang] = [{'url': subtitle['href']}] if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
'url': subtitle_href,
'ext': mimetype2ext(subtitle.get('type')) or determine_ext(subtitle_href),
})
formats = [] formats = []
media_content = get_media_node('content') media_content = get_media_node('content')

66
youtube_dl/extractor/anvato.py
View File

@ -5,6 +5,7 @@ import base64
import hashlib import hashlib
import json import json
import random import random
import re
import time import time
from .common import InfoExtractor from .common import InfoExtractor
@ -16,6 +17,7 @@ from ..utils import (
intlist_to_bytes, intlist_to_bytes,
int_or_none, int_or_none,
strip_jsonp, strip_jsonp,
unescapeHTML,
) )
@ -26,6 +28,8 @@ def md5_text(s):
class AnvatoIE(InfoExtractor): class AnvatoIE(InfoExtractor):
_VALID_URL = r'anvato:(?P<access_key_or_mcp>[^:]+):(?P<id>\d+)'
# Copied from anvplayer.min.js # Copied from anvplayer.min.js
_ANVACK_TABLE = { _ANVACK_TABLE = {
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ', 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
@ -114,6 +118,22 @@ class AnvatoIE(InfoExtractor):
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ' 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
} }
_MCP_TO_ACCESS_KEY_TABLE = {
'qa': 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922',
'lin': 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749',
'univison': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'uni': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'dev': 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a',
'sps': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'spsstg': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'anv': 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3',
'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
}
_ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
@ -178,12 +198,7 @@ class AnvatoIE(InfoExtractor):
} }
if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'): if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
# Not using _extract_m3u8_formats here as individual media if tbr is not None:
# playlists are also included in published_urls.
if tbr is None:
formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls'))
continue
else:
a_format.update({ a_format.update({
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])), 'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4', 'ext': 'mp4',
@ -222,9 +237,42 @@ class AnvatoIE(InfoExtractor):
'subtitles': subtitles, 'subtitles': subtitles,
} }
@staticmethod
def _extract_urls(ie, webpage, video_id):
entries = []
for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
anvplayer_data = ie._parse_json(
mobj.group('anvp'), video_id, transform_source=unescapeHTML,
fatal=False)
if not anvplayer_data:
continue
video = anvplayer_data.get('video')
if not isinstance(video, compat_str) or not video.isdigit():
continue
access_key = anvplayer_data.get('accessKey')
if not access_key:
mcp = anvplayer_data.get('mcp')
if mcp:
access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
mcp.lower())
if not access_key:
continue
entries.append(ie.url_result(
'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
video_id=video))
return entries
def _extract_anvato_videos(self, webpage, video_id): def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(self._html_search_regex( anvplayer_data = self._parse_json(
r'<script[^>]+data-anvp=\'([^\']+)\'', webpage, self._html_search_regex(
'Anvato player data'), video_id) self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
video_id)
return self._get_anvato_videos( return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video']) anvplayer_data['accessKey'], anvplayer_data['video'])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
access_key, video_id = mobj.group('access_key_or_mcp', 'id')
if access_key not in self._ANVACK_TABLE:
access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key]
return self._get_anvato_videos(access_key, video_id)

4
youtube_dl/extractor/appleconnect.py
View File

@ -12,13 +12,13 @@ class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)' _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
_TEST = { _TEST = {
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3', 'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': '10d0f2799111df4cb1c924520ca78f98', 'md5': 'e7c38568a01ea45402570e6029206723',
'info_dict': { 'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3', 'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'ext': 'm4v', 'ext': 'm4v',
'title': 'Energy', 'title': 'Energy',
'uploader': 'Drake', 'uploader': 'Drake',
'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg', 'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20150710', 'upload_date': '20150710',
'timestamp': 1436545535, 'timestamp': 1436545535,
}, },

5
youtube_dl/extractor/appletrailers.py
View File

@ -70,7 +70,8 @@ class AppleTrailersIE(InfoExtractor):
}, { }, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/', 'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': { 'info_dict': {
'id': 'blackthorn', 'id': '4489',
'title': 'Blackthorn',
}, },
'playlist_mincount': 2, 'playlist_mincount': 2,
'expected_warnings': ['Unable to download JSON metadata'], 'expected_warnings': ['Unable to download JSON metadata'],
@ -261,7 +262,7 @@ class AppleTrailersSectionIE(InfoExtractor):
'title': 'Most Popular', 'title': 'Most Popular',
'id': 'mostpopular', 'id': 'mostpopular',
}, },
'playlist_mincount': 80, 'playlist_mincount': 30,
}, { }, {
'url': 'http://trailers.apple.com/#section=moviestudios', 'url': 'http://trailers.apple.com/#section=moviestudios',
'info_dict': { 'info_dict': {

4
youtube_dl/extractor/archiveorg.py
View File

@ -24,12 +24,12 @@ class ArchiveOrgIE(InfoExtractor):
} }
}, { }, {
'url': 'https://archive.org/details/Cops1922', 'url': 'https://archive.org/details/Cops1922',
'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba', 'md5': '0869000b4ce265e8ca62738b336b268a',
'info_dict': { 'info_dict': {
'id': 'Cops1922', 'id': 'Cops1922',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)', 'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:b4544662605877edd99df22f9620d858', 'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
} }
}, { }, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect', 'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',

5
youtube_dl/extractor/arte.py
View File

@ -180,7 +180,7 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE): class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7' IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D', 'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
@ -188,6 +188,9 @@ class ArteTVPlus7IE(ArteTVBaseIE):
}, { }, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22', 'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
}] }]
@classmethod @classmethod

2
youtube_dl/extractor/atresplayer.py
View File

@ -36,7 +36,7 @@ class AtresPlayerIE(InfoExtractor):
}, },
{ {
'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
'md5': '0d0e918533bbd4b263f2de4d197d4aac', 'md5': '6e52cbb513c405e403dbacb7aacf8747',
'info_dict': { 'info_dict': {
'id': 'capitulo-112-david-bustamante', 'id': 'capitulo-112-david-bustamante',
'ext': 'flv', 'ext': 'flv',

2
youtube_dl/extractor/audioboom.py
View File

@ -16,7 +16,7 @@ class AudioBoomIE(InfoExtractor):
'title': '3/09/2016 Czaban Hour 3', 'title': '3/09/2016 Czaban Hour 3',
'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans',
'duration': 2245.72, 'duration': 2245.72,
'uploader': 'Steve Czaban', 'uploader': 'SB Nation A.M.',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
} }
}, { }, {

140
youtube_dl/extractor/azubu.py
View File

@ -1,140 +0,0 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
)
class AzubuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
'md5': 'a88b42fcf844f29ad6035054bd9ecaf4',
'info_dict': {
'id': '15575',
'ext': 'mp4',
'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1',
'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01',
'thumbnail': r're:^https?://.*\.jpe?g',
'timestamp': 1417523507.334,
'upload_date': '20141202',
'duration': 9988.7,
'uploader': 'GSL',
'uploader_id': 414310,
'view_count': int,
},
},
{
'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-',
'md5': 'b72a871fe1d9f70bd7673769cdb3b925',
'info_dict': {
'id': '9344',
'ext': 'mp4',
'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"',
'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af',
'thumbnail': r're:^https?://.*\.jpe?g',
'timestamp': 1410530893.320,
'upload_date': '20140912',
'duration': 172.385,
'uploader': 'FnaticTV',
'uploader_id': 272749,
'view_count': int,
},
'skip': 'Channel offline',
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
title = data['title'].strip()
description = data.get('description')
thumbnail = data.get('thumbnail')
view_count = data.get('view_count')
user = data.get('user', {})
uploader = user.get('username')
uploader_id = user.get('id')
stream_params = json.loads(data['stream_params'])
timestamp = float_or_none(stream_params.get('creationDate'), 1000)
duration = float_or_none(stream_params.get('length'), 1000)
renditions = stream_params.get('renditions') or []
video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
if video:
renditions.append(video)
if not renditions and not user.get('channel', {}).get('is_live', True):
raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True)
formats = [{
'url': fmt['url'],
'width': fmt['frameWidth'],
'height': fmt['frameHeight'],
'vbr': float_or_none(fmt['encodingRate'], 1000),
'filesize': fmt['size'],
'vcodec': fmt['videoCodec'],
'container': fmt['videoContainer'],
} for fmt in renditions if fmt['url']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'formats': formats,
}
class AzubuLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$'
_TESTS = [{
'url': 'http://www.azubu.tv/MarsTVMDLen',
'only_matching': True,
}, {
'url': 'http://azubu.uol.com.br/adolfz',
'only_matching': True,
}]
def _real_extract(self, url):
user = self._match_id(url)
info = self._download_json(
'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user),
user)['data']
if info['type'] != 'STREAM':
raise ExtractorError('{0} is not streaming live'.format(user), expected=True)
req = sanitized_Request(
'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id'])
req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV')
bc_info = self._download_json(req, user)
m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
self._sort_formats(formats)
return {
'id': info['id'],
'title': self._live_title(info['title']),
'uploader_id': user,
'formats': formats,
'is_live': True,
'thumbnail': bc_info['poster'],
}

8
youtube_dl/extractor/bandcamp.py
View File

@ -34,12 +34,12 @@ class BandcampIE(InfoExtractor):
'_skip': 'There is a limit of 200 free downloads / month for the test song' '_skip': 'There is a limit of 200 free downloads / month for the test song'
}, { }, {
'url': 'http://benprunty.bandcamp.com/track/lanius-battle', 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'md5': '73d0b3171568232574e45652f8720b5c', 'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
'info_dict': { 'info_dict': {
'id': '2650410135', 'id': '2650410135',
'ext': 'mp3', 'ext': 'aiff',
'title': 'Lanius (Battle)', 'title': 'Ben Prunty - Lanius (Battle)',
'uploader': 'Ben Prunty Music', 'uploader': 'Ben Prunty',
}, },
}] }]

2
youtube_dl/extractor/beeg.py
View File

@ -16,7 +16,7 @@ class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://beeg.com/5416503', 'url': 'http://beeg.com/5416503',
'md5': '46c384def73b33dbc581262e5ee67cef', 'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': { 'info_dict': {
'id': '5416503', 'id': '5416503',
'ext': 'mp4', 'ext': 'mp4',

10
youtube_dl/extractor/bleacherreport.py
View File

@ -35,7 +35,7 @@ class BleacherReportIE(InfoExtractor):
'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
'timestamp': 1446839961, 'timestamp': 1446839961,
'uploader': 'Sean Fay', 'uploader': 'Sean Fay',
'description': 'md5:825e94e0f3521df52fa83b2ed198fa20', 'description': 'md5:b1601e2314c4d8eec23b6eafe086a757',
'uploader_id': 6466954, 'uploader_id': 6466954,
'upload_date': '20151011', 'upload_date': '20151011',
}, },
@ -90,17 +90,13 @@ class BleacherReportCMSIE(AMPIE):
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})' _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
_TESTS = [{ _TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1', 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'md5': '8c2c12e3af7805152675446c905d159b', 'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
'info_dict': { 'info_dict': {
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'ext': 'mp4', 'ext': 'flv',
'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
}, },
'params': {
# m3u8 download
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):

2
youtube_dl/extractor/br.py
View File

@ -77,7 +77,7 @@ class BRIE(InfoExtractor):
'description': 'md5:bb659990e9e59905c3d41e369db1fbe3', 'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
'duration': 893, 'duration': 893,
'uploader': 'Eva Maria Steimle', 'uploader': 'Eva Maria Steimle',
'upload_date': '20140117', 'upload_date': '20170208',
} }
}, },
] ]

26
youtube_dl/extractor/brightcove.py
View File

@ -131,6 +131,12 @@ class BrightcoveLegacyIE(InfoExtractor):
}, },
'playlist_mincount': 10, 'playlist_mincount': 10,
}, },
{
# playerID inferred from bcpid
# from http://www.un.org/chinese/News/story.asp?NewsID=27724
'url': 'https://link.brightcove.com/services/player/bcpid1722935254001/?bctid=5360463607001&autoStart=false&secureConnections=true&width=650&height=350',
'only_matching': True, # Tested in GenericIE
}
] ]
FLV_VCODECS = { FLV_VCODECS = {
1: 'SORENSON', 1: 'SORENSON',
@ -266,9 +272,13 @@ class BrightcoveLegacyIE(InfoExtractor):
if matches: if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches])) return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
return list(filter(None, [ matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)
cls._build_brighcove_url_from_js(custom_bc) if matches:
for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)])) return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
for custom_bc in matches]))
return [src for _, src in re.findall(
r'<iframe[^>]+src=([\'"])((?:https?:)?//link\.brightcove\.com/services/player/(?!\1).+)\1', webpage)]
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
@ -285,6 +295,10 @@ class BrightcoveLegacyIE(InfoExtractor):
if videoPlayer: if videoPlayer:
# We set the original url as the default 'Referer' header # We set the original url as the default 'Referer' header
referer = smuggled_data.get('Referer', url) referer = smuggled_data.get('Referer', url)
if 'playerID' not in query:
mobj = re.search(r'/bcpid(\d+)', url)
if mobj is not None:
query['playerID'] = [mobj.group(1)]
return self._get_video_info( return self._get_video_info(
videoPlayer[0], query, referer=referer) videoPlayer[0], query, referer=referer)
elif 'playerKey' in query: elif 'playerKey' in query:
@ -484,8 +498,8 @@ class BrightcoveNewIE(InfoExtractor):
}] }]
@staticmethod @staticmethod
def _extract_url(webpage): def _extract_url(ie, webpage):
urls = BrightcoveNewIE._extract_urls(webpage) urls = BrightcoveNewIE._extract_urls(ie, webpage)
return urls[0] if urls else None return urls[0] if urls else None
@staticmethod @staticmethod
@ -508,7 +522,7 @@ class BrightcoveNewIE(InfoExtractor):
# [2] looks like: # [2] looks like:
for video, script_tag, account_id, player_id, embed in re.findall( for video, script_tag, account_id, player_id, embed in re.findall(
r'''(?isx) r'''(?isx)
(<video\s+[^>]+>) (<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
(?:.*? (?:.*?
(<script[^>]+ (<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/ src=["\'](?:https?:)?//players\.brightcove\.net/

5
youtube_dl/extractor/canalc2.py
View File

@ -16,13 +16,10 @@ class Canalc2IE(InfoExtractor):
'md5': '060158428b650f896c542dfbb3d6487f', 'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': { 'info_dict': {
'id': '12163', 'id': '12163',
'ext': 'flv', 'ext': 'mp4',
'title': 'Terrasses du Numérique', 'title': 'Terrasses du Numérique',
'duration': 122, 'duration': 122,
}, },
'params': {
'skip_download': True, # Requires rtmpdump
}
}, { }, {
'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui', 'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
'only_matching': True, 'only_matching': True,

6
youtube_dl/extractor/cbc.py
View File

@ -96,6 +96,7 @@ class CBCIE(InfoExtractor):
'info_dict': { 'info_dict': {
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks', 'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
'id': 'dog-indoor-exercise-winter-1.3928238', 'id': 'dog-indoor-exercise-winter-1.3928238',
'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
}, },
'playlist_mincount': 6, 'playlist_mincount': 6,
}] }]
@ -165,12 +166,11 @@ class CBCPlayerIE(InfoExtractor):
'uploader': 'CBCC-NEW', 'uploader': 'CBCC-NEW',
}, },
}, { }, {
# available only when we add `formats=MPEG4,FLV,MP3` to theplatform url
'url': 'http://www.cbc.ca/player/play/2164402062', 'url': 'http://www.cbc.ca/player/play/2164402062',
'md5': '17a61eb813539abea40618d6323a7f82', 'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': { 'info_dict': {
'id': '2164402062', 'id': '2164402062',
'ext': 'flv', 'ext': 'mp4',
'title': 'Cancer survivor four times over', 'title': 'Cancer survivor four times over',
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.', 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746, 'timestamp': 1320410746,

4
youtube_dl/extractor/cbslocal.py
View File

@ -60,8 +60,8 @@ class CBSLocalIE(AnvatoIE):
'title': 'A Very Blue Anniversary', 'title': 'A Very Blue Anniversary',
'description': 'CBS2’s Cindy Hsu has more.', 'description': 'CBS2’s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*', 'thumbnail': 're:^https?://.*',
'timestamp': 1479962220, 'timestamp': int,
'upload_date': '20161124', 'upload_date': r're:^\d{8}$',
'uploader': 'CBS', 'uploader': 'CBS',
'subtitles': { 'subtitles': {
'en': 'mincount:5', 'en': 'mincount:5',

52
youtube_dl/extractor/cda.py
View File

@ -9,7 +9,10 @@ from ..utils import (
ExtractorError, ExtractorError,
float_or_none, float_or_none,
int_or_none, int_or_none,
multipart_encode,
parse_duration, parse_duration,
random_birthday,
urljoin,
) )
@ -27,7 +30,8 @@ class CDAIE(InfoExtractor):
'description': 'md5:269ccd135d550da90d1662651fcb9772', 'description': 'md5:269ccd135d550da90d1662651fcb9772',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'average_rating': float, 'average_rating': float,
'duration': 39 'duration': 39,
'age_limit': 0,
} }
}, { }, {
'url': 'http://www.cda.pl/video/57413289', 'url': 'http://www.cda.pl/video/57413289',
@ -41,13 +45,41 @@ class CDAIE(InfoExtractor):
'uploader': 'crash404', 'uploader': 'crash404',
'view_count': int, 'view_count': int,
'average_rating': float, 'average_rating': float,
'duration': 137 'duration': 137,
'age_limit': 0,
} }
}, {
# Age-restricted
'url': 'http://www.cda.pl/video/1273454c4',
'info_dict': {
'id': '1273454c4',
'ext': 'mp4',
'title': 'Bronson (2008) napisy HD 1080p',
'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
'height': 1080,
'uploader': 'boniek61',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 5554,
'age_limit': 18,
'view_count': int,
'average_rating': float,
},
}, { }, {
'url': 'http://ebd.cda.pl/0x0/5749950c', 'url': 'http://ebd.cda.pl/0x0/5749950c',
'only_matching': True, 'only_matching': True,
}] }]
def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
form_data = random_birthday('rok', 'miesiac', 'dzien')
form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
data, content_type = multipart_encode(form_data)
return self._download_webpage(
urljoin(url, '/a/validatebirth'), video_id, *args,
data=data, headers={
'Referer': url,
'Content-Type': content_type,
}, **kwargs)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
self._set_cookie('cda.pl', 'cda.player', 'html5') self._set_cookie('cda.pl', 'cda.player', 'html5')
@ -57,6 +89,13 @@ class CDAIE(InfoExtractor):
if 'Ten film jest dostępny dla użytkowników premium' in webpage: if 'Ten film jest dostępny dla użytkowników premium' in webpage:
raise ExtractorError('This video is only available for premium users.', expected=True) raise ExtractorError('This video is only available for premium users.', expected=True)
need_confirm_age = False
if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
webpage, 'birthday validate form', default=None):
webpage = self._download_age_confirm_page(
url, video_id, note='Confirming age')
need_confirm_age = True
formats = [] formats = []
uploader = self._search_regex(r'''(?x) uploader = self._search_regex(r'''(?x)
@ -81,6 +120,7 @@ class CDAIE(InfoExtractor):
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats, 'formats': formats,
'duration': None, 'duration': None,
'age_limit': 18 if need_confirm_age else 0,
} }
def extract_format(page, version): def extract_format(page, version):
@ -121,7 +161,12 @@ class CDAIE(InfoExtractor):
for href, resolution in re.findall( for href, resolution in re.findall(
r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)', r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
webpage): webpage):
webpage = self._download_webpage( if need_confirm_age:
handler = self._download_age_confirm_page
else:
handler = self._download_webpage
webpage = handler(
self._BASE_URL + href, video_id, self._BASE_URL + href, video_id,
'Downloading %s version information' % resolution, fatal=False) 'Downloading %s version information' % resolution, fatal=False)
if not webpage: if not webpage:
@ -129,6 +174,7 @@ class CDAIE(InfoExtractor):
# invalid version is requested. # invalid version is requested.
self.report_warning('Unable to download %s version information' % resolution) self.report_warning('Unable to download %s version information' % resolution)
continue continue
extract_format(webpage, resolution) extract_format(webpage, resolution)
self._sort_formats(formats) self._sort_formats(formats)

2
youtube_dl/extractor/clipfish.py
View File

@ -12,7 +12,7 @@ class ClipfishIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
_TEST = { _TEST = {
'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/', 'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/',
'md5': '720563e467b86374c194bdead08d207d', 'md5': 'b9a5dc46294154c1193e2d10e0c95693',
'info_dict': { 'info_dict': {
'id': '4343170', 'id': '4343170',
'ext': 'mp4', 'ext': 'mp4',

3
youtube_dl/extractor/collegerama.py
View File

@ -21,7 +21,7 @@ class CollegeRamaIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.', 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
'description': '', 'description': '',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
'duration': 7713.088, 'duration': 7713.088,
'timestamp': 1413309600, 'timestamp': 1413309600,
'upload_date': '20141014', 'upload_date': '20141014',
@ -35,6 +35,7 @@ class CollegeRamaIE(InfoExtractor):
'ext': 'wmv', 'ext': 'wmv',
'title': '64ste Vakantiecursus: Afvalwater', 'title': '64ste Vakantiecursus: Afvalwater',
'description': 'md5:7fd774865cc69d972f542b157c328305', 'description': 'md5:7fd774865cc69d972f542b157c328305',
'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
'duration': 10853, 'duration': 10853,
'timestamp': 1326446400, 'timestamp': 1326446400,
'upload_date': '20120113', 'upload_date': '20120113',

213
youtube_dl/extractor/common.py
View File

@ -245,6 +245,10 @@ class InfoExtractor(object):
specified in the URL. specified in the URL.
end_time: Time in seconds where the reproduction should end, as end_time: Time in seconds where the reproduction should end, as
specified in the URL. specified in the URL.
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
* "title" (optional, string)
The following fields should only be used when the video belongs to some logical The following fields should only be used when the video belongs to some logical
chapter or section: chapter or section:
@ -976,6 +980,23 @@ class InfoExtractor(object):
return info return info
if isinstance(json_ld, dict): if isinstance(json_ld, dict):
json_ld = [json_ld] json_ld = [json_ld]
def extract_video_object(e):
assert e['@type'] == 'VideoObject'
info.update({
'url': e.get('contentUrl'),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
'view_count': int_or_none(e.get('interactionCount')),
})
for e in json_ld: for e in json_ld:
if e.get('@context') == 'http://schema.org': if e.get('@context') == 'http://schema.org':
item_type = e.get('@type') item_type = e.get('@type')
@ -1000,18 +1021,11 @@ class InfoExtractor(object):
'description': unescapeHTML(e.get('articleBody')), 'description': unescapeHTML(e.get('articleBody')),
}) })
elif item_type == 'VideoObject': elif item_type == 'VideoObject':
info.update({ extract_video_object(e)
'url': e.get('contentUrl'), elif item_type == 'WebPage':
'title': unescapeHTML(e.get('name')), video = e.get('video')
'description': unescapeHTML(e.get('description')), if isinstance(video, dict) and video.get('@type') == 'VideoObject':
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'), extract_video_object(video)
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
})
break break
return dict((k, v) for k, v in info.items() if v is not None) return dict((k, v) for k, v in info.items() if v is not None)
@ -1303,40 +1317,50 @@ class InfoExtractor(object):
entry_protocol='m3u8', preference=None, entry_protocol='m3u8', preference=None,
m3u8_id=None, note=None, errnote=None, m3u8_id=None, note=None, errnote=None,
fatal=True, live=False): fatal=True, live=False):
res = self._download_webpage_handle( res = self._download_webpage_handle(
m3u8_url, video_id, m3u8_url, video_id,
note=note or 'Downloading m3u8 information', note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information', errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal) fatal=fatal)
if res is False: if res is False:
return [] return []
m3u8_doc, urlh = res m3u8_doc, urlh = res
m3u8_url = urlh.geturl() m3u8_url = urlh.geturl()
return self._parse_m3u8_formats(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
preference=preference, m3u8_id=m3u8_id, live=live)
def _parse_m3u8_formats(self, m3u8_doc, m3u8_url, ext=None,
entry_protocol='m3u8', preference=None,
m3u8_id=None, live=False):
if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access
return [] return []
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)] formats = []
format_url = lambda u: ( format_url = lambda u: (
u u
if re.match(r'^https?://', u) if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u)) else compat_urlparse.urljoin(m3u8_url, u))
# We should try extracting formats only from master playlists [1], i.e. # References:
# playlists that describe available qualities. On the other hand media # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21
# playlists [2] should be returned as is since they contain just the media # 2. https://github.com/rg3/youtube-dl/issues/12211
# without qualities renditions.
# We should try extracting formats only from master playlists [1, 4.3.4],
# i.e. playlists that describe available qualities. On the other hand
# media playlists [1, 4.3.3] should be returned as is since they contain
# just the media without qualities renditions.
# Fortunately, master playlist can be easily distinguished from media # Fortunately, master playlist can be easily distinguished from media
# playlist based on particular tags availability. As of [1, 2] master # playlist based on particular tags availability. As of [1, 4.3.3, 4.3.4]
# playlist tags MUST NOT appear in a media playist and vice versa. # master playlist tags MUST NOT appear in a media playist and vice versa.
# As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist # As of [1, 4.3.3.1] #EXT-X-TARGETDURATION tag is REQUIRED for every
# and MUST NOT appear in master playlist thus we can clearly detect media # media playlist and MUST NOT appear in master playlist thus we can
# playlist with this criterion. # clearly detect media playlist with this criterion.
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is
return [{ return [{
'url': m3u8_url, 'url': m3u8_url,
@ -1345,52 +1369,72 @@ class InfoExtractor(object):
'protocol': entry_protocol, 'protocol': entry_protocol,
'preference': preference, 'preference': preference,
}] }]
audio_in_video_stream = {}
last_info = {} groups = {}
last_media = {} last_stream_inf = {}
def extract_media(x_media_line):
media = parse_m3u8_attributes(x_media_line)
# As per [1, 4.3.4.1] TYPE, GROUP-ID and NAME are REQUIRED
media_type, group_id, name = media.get('TYPE'), media.get('GROUP-ID'), media.get('NAME')
if not (media_type and group_id and name):
return
groups.setdefault(group_id, []).append(media)
if media_type not in ('VIDEO', 'AUDIO'):
return
media_url = media.get('URI')
if media_url:
format_id = []
for v in (group_id, name):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'manifest_url': m3u8_url,
'language': media.get('LANGUAGE'),
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
}
if media_type == 'AUDIO':
f['vcodec'] = 'none'
formats.append(f)
def build_stream_name():
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF tag it still sometimes may be present (see [1]
# or vidio test in TestInfoExtractor.test_parse_m3u8_formats)
# 1. http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
stream_name = last_stream_inf.get('NAME')
if stream_name:
return stream_name
# If there is no NAME in EXT-X-STREAM-INF it will be obtained
# from corresponding rendition group
stream_group_id = last_stream_inf.get('VIDEO')
if not stream_group_id:
return
stream_group = groups.get(stream_group_id)
if not stream_group:
return stream_group_id
rendition = stream_group[0]
return rendition.get('NAME') or stream_group_id
for line in m3u8_doc.splitlines(): for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'): if line.startswith('#EXT-X-STREAM-INF:'):
last_info = parse_m3u8_attributes(line) last_stream_inf = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'): elif line.startswith('#EXT-X-MEDIA:'):
media = parse_m3u8_attributes(line) extract_media(line)
media_type = media.get('TYPE')
if media_type in ('VIDEO', 'AUDIO'):
group_id = media.get('GROUP-ID')
media_url = media.get('URI')
if media_url:
format_id = []
for v in (group_id, media.get('NAME')):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'language': media.get('LANGUAGE'),
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
}
if media_type == 'AUDIO':
f['vcodec'] = 'none'
if group_id and not audio_in_video_stream.get(group_id):
audio_in_video_stream[group_id] = False
formats.append(f)
else:
# When there is no URI in EXT-X-MEDIA let this tag's
# data be used by regular URI lines below
last_media = media
if media_type == 'AUDIO' and group_id:
audio_in_video_stream[group_id] = True
elif line.startswith('#') or not line.strip(): elif line.startswith('#') or not line.strip():
continue continue
else: else:
tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000) tbr = float_or_none(
last_stream_inf.get('AVERAGE-BANDWIDTH') or
last_stream_inf.get('BANDWIDTH'), scale=1000)
format_id = [] format_id = []
if m3u8_id: if m3u8_id:
format_id.append(m3u8_id) format_id.append(m3u8_id)
# Despite specification does not mention NAME attribute for stream_name = build_stream_name()
# EXT-X-STREAM-INF it still sometimes may be present
stream_name = last_info.get('NAME') or last_media.get('NAME')
# Bandwidth of live streams may differ over time thus making # Bandwidth of live streams may differ over time thus making
# format_id unpredictable. So it's better to keep provided # format_id unpredictable. So it's better to keep provided
# format_id intact. # format_id intact.
@ -1400,14 +1444,14 @@ class InfoExtractor(object):
f = { f = {
'format_id': '-'.join(format_id), 'format_id': '-'.join(format_id),
'url': manifest_url, 'url': manifest_url,
'manifest_url': manifest_url, 'manifest_url': m3u8_url,
'tbr': tbr, 'tbr': tbr,
'ext': ext, 'ext': ext,
'fps': float_or_none(last_info.get('FRAME-RATE')), 'fps': float_or_none(last_stream_inf.get('FRAME-RATE')),
'protocol': entry_protocol, 'protocol': entry_protocol,
'preference': preference, 'preference': preference,
} }
resolution = last_info.get('RESOLUTION') resolution = last_stream_inf.get('RESOLUTION')
if resolution: if resolution:
mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution) mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
if mobj: if mobj:
@ -1423,13 +1467,26 @@ class InfoExtractor(object):
'vbr': vbr, 'vbr': vbr,
'abr': abr, 'abr': abr,
}) })
f.update(parse_codecs(last_info.get('CODECS'))) codecs = parse_codecs(last_stream_inf.get('CODECS'))
if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none': f.update(codecs)
# TODO: update acodec for audio only formats with the same GROUP-ID audio_group_id = last_stream_inf.get('AUDIO')
f['acodec'] = 'none' # As per [1, 4.3.4.1.1] any EXT-X-STREAM-INF tag which
# references a rendition group MUST have a CODECS attribute.
# However, this is not always respected, for example, [2]
# contains EXT-X-STREAM-INF tag which references AUDIO
# rendition group but does not have CODECS and despite
# referencing audio group an audio group, it represents
# a complete (with audio and video) format. So, for such cases
# we will ignore references to rendition groups and treat them
# as complete formats.
if audio_group_id and codecs and f.get('vcodec') != 'none':
audio_group = groups.get(audio_group_id)
if audio_group and audio_group[0].get('URI'):
# TODO: update acodec for audio only formats with
# the same GROUP-ID
f['acodec'] = 'none'
formats.append(f) formats.append(f)
last_info = {} last_stream_inf = {}
last_media = {}
return formats return formats
@staticmethod @staticmethod
@ -1803,7 +1860,7 @@ class InfoExtractor(object):
'ext': mimetype2ext(mime_type), 'ext': mimetype2ext(mime_type),
'width': int_or_none(representation_attrib.get('width')), 'width': int_or_none(representation_attrib.get('width')),
'height': int_or_none(representation_attrib.get('height')), 'height': int_or_none(representation_attrib.get('height')),
'tbr': int_or_none(bandwidth, 1000), 'tbr': float_or_none(bandwidth, 1000),
'asr': int_or_none(representation_attrib.get('audioSamplingRate')), 'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
'fps': int_or_none(representation_attrib.get('frameRate')), 'fps': int_or_none(representation_attrib.get('frameRate')),
'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None, 'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
@ -2182,7 +2239,7 @@ class InfoExtractor(object):
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json): def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search( mobj = re.search(
r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)', r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
webpage) webpage)
if mobj: if mobj:
try: try:
@ -2258,11 +2315,17 @@ class InfoExtractor(object):
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None, def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None): m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
urls = []
formats = [] formats = []
for source in jwplayer_sources_data: for source in jwplayer_sources_data:
source_url = self._proto_relative_url(source['file']) source_url = self._proto_relative_url(source.get('file'))
if not source_url:
continue
if base_url: if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url) source_url = compat_urlparse.urljoin(base_url, source_url)
if source_url in urls:
continue
urls.append(source_url)
source_type = source.get('type') or '' source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url) ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8': if source_type == 'hls' or ext == 'm3u8':

5
youtube_dl/extractor/coub.py
View File

@ -24,12 +24,11 @@ class CoubIE(InfoExtractor):
'duration': 4.6, 'duration': 4.6,
'timestamp': 1428527772, 'timestamp': 1428527772,
'upload_date': '20150408', 'upload_date': '20150408',
'uploader': 'Артём Лоскутников', 'uploader': 'Artyom Loskutnikov',
'uploader_id': 'artyom.loskutnikov', 'uploader_id': 'artyom.loskutnikov',
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int,
'age_limit': 0, 'age_limit': 0,
}, },
}, { }, {
@ -118,7 +117,6 @@ class CoubIE(InfoExtractor):
view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count')) view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count'))
like_count = int_or_none(coub.get('likes_count')) like_count = int_or_none(coub.get('likes_count'))
repost_count = int_or_none(coub.get('recoubs_count')) repost_count = int_or_none(coub.get('recoubs_count'))
comment_count = int_or_none(coub.get('comments_count'))
age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin')) age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin'))
if age_restricted is not None: if age_restricted is not None:
@ -137,7 +135,6 @@ class CoubIE(InfoExtractor):
'view_count': view_count, 'view_count': view_count,
'like_count': like_count, 'like_count': like_count,
'repost_count': repost_count, 'repost_count': repost_count,
'comment_count': comment_count,
'age_limit': age_limit, 'age_limit': age_limit,
'formats': formats, 'formats': formats,
} }

4
youtube_dl/extractor/crunchyroll.py
View File

@ -171,7 +171,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'info_dict': { 'info_dict': {
'id': '727589', 'id': '727589',
'ext': 'mp4', 'ext': 'mp4',
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!", 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!",
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d', 'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Kadokawa Pictures Inc.', 'uploader': 'Kadokawa Pictures Inc.',
@ -179,7 +179,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'series': "KONOSUBA -God's blessing on this wonderful world!", 'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2", 'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2, 'season_number': 2,
'episode': 'Give Me Deliverance from this Judicial Injustice!', 'episode': 'Give Me Deliverance From This Judicial Injustice!',
'episode_number': 1, 'episode_number': 1,
}, },
'params': { 'params': {

21
youtube_dl/extractor/dailymotion.py
View File

@ -50,6 +50,24 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
] ]
_TESTS = [ _TESTS = [
{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'info_dict': {
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 187,
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
'uploader_id': 'x1xm8ri',
'age_limit': 0,
'view_count': int,
},
},
{ {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames', 'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
'md5': '2137c41a8e78554bb09225b8eb322406', 'md5': '2137c41a8e78554bb09225b8eb322406',
@ -66,7 +84,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader_id': 'xijv66', 'uploader_id': 'xijv66',
'age_limit': 0, 'age_limit': 0,
'view_count': int, 'view_count': int,
} },
'skip': 'video gone',
}, },
# Vevo video # Vevo video
{ {

3
youtube_dl/extractor/democracynow.py
View File

@ -21,7 +21,8 @@ class DemocracynowIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '2015-0703-001', 'id': '2015-0703-001',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Daily Show', 'title': 'Daily Show for July 03, 2015',
'description': 'md5:80eb927244d6749900de6072c7cc2c86',
}, },
}, { }, {
'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree', 'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',

2
youtube_dl/extractor/dotsub.py
View File

@ -35,7 +35,7 @@ class DotsubIE(InfoExtractor):
'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p', 'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
'duration': 290, 'duration': 290,
'timestamp': 1476767794.2809999, 'timestamp': 1476767794.2809999,
'upload_date': '20160525', 'upload_date': '20161018',
'uploader': 'parthivi001', 'uploader': 'parthivi001',
'uploader_id': 'user52596202', 'uploader_id': 'user52596202',
'view_count': int, 'view_count': int,

4
youtube_dl/extractor/douyutv.py
View File

@ -20,7 +20,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732', 'id': '17732',
'display_id': 'iseven', 'display_id': 'iseven',
'ext': 'flv', 'ext': 'flv',
'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*', 'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅', 'uploader': '7师傅',
@ -51,7 +51,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732', 'id': '17732',
'display_id': '17732', 'display_id': '17732',
'ext': 'flv', 'ext': 'flv',
'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*', 'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅', 'uploader': '7师傅',

10
youtube_dl/extractor/extractors.py
View File

@ -41,6 +41,7 @@ from .alphaporno import AlphaPornoIE
from .amcnetworks import AMCNetworksIE from .amcnetworks import AMCNetworksIE
from .animeondemand import AnimeOnDemandIE from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE from .anitube import AnitubeIE
from .anvato import AnvatoIE
from .anysex import AnySexIE from .anysex import AnySexIE
from .aol import AolIE from .aol import AolIE
from .allocine import AllocineIE from .allocine import AllocineIE
@ -87,7 +88,6 @@ from .azmedien import (
AZMedienPlaylistIE, AZMedienPlaylistIE,
AZMedienShowPlaylistIE, AZMedienShowPlaylistIE,
) )
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE from .bandcamp import BandcampIE, BandcampAlbumIE
@ -663,6 +663,7 @@ from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE from .nobelprize import NobelPrizeIE
from .noco import NocoIE from .noco import NocoIE
from .noovo import NoovoIE
from .normalboots import NormalbootsIE from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE from .nosvideo import NosVideoIE
from .nova import NovaIE from .nova import NovaIE
@ -939,6 +940,7 @@ from .srmediathek import SRMediathekIE
from .stanfordoc import StanfordOpenClassroomIE from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE from .steam import SteamIE
from .streamable import StreamableIE from .streamable import StreamableIE
from .streamango import StreamangoIE
from .streamcloud import StreamcloudIE from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE from .streetvoice import StreetVoiceIE
@ -1233,7 +1235,10 @@ from .wrzuta import (
WrzutaIE, WrzutaIE,
WrzutaPlaylistIE, WrzutaPlaylistIE,
) )
from .wsj import WSJIE from .wsj import (
WSJIE,
WSJArticleIE,
)
from .xbef import XBefIE from .xbef import XBefIE
from .xboxclips import XboxClipsIE from .xboxclips import XboxClipsIE
from .xfileshare import XFileShareIE from .xfileshare import XFileShareIE
@ -1295,5 +1300,6 @@ from .youtube import (
YoutubeWatchLaterIE, YoutubeWatchLaterIE,
) )
from .zapiks import ZapiksIE from .zapiks import ZapiksIE
from .zaq1 import Zaq1IE
from .zdf import ZDFIE, ZDFChannelIE from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import ZingMp3IE from .zingmp3 import ZingMp3IE

9
youtube_dl/extractor/foxsports.py
View File

@ -11,10 +11,10 @@ class FoxSportsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_TEST = { _TEST = {
'url': 'http://www.foxsports.com/video?vid=432609859715', 'url': 'http://www.foxsports.com/tennessee/video/432609859715',
'md5': 'b49050e955bebe32c301972e4012ac17', 'md5': 'b49050e955bebe32c301972e4012ac17',
'info_dict': { 'info_dict': {
'id': 'i0qKWsk3qJaM', 'id': 'bwduI3X_TgUB',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Courtney Lee on going up 2-0 in series vs. Blazers', 'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
'description': 'Courtney Lee talks about Memphis being focused.', 'description': 'Courtney Lee talks about Memphis being focused.',
@ -31,8 +31,9 @@ class FoxSportsIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
config = self._parse_json( config = self._parse_json(
self._search_regex( self._html_search_regex(
r"data-player-config='([^']+)'", webpage, 'data player config'), r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""",
webpage, 'data player config'),
video_id) video_id)
return self.url_result(smuggle_url(update_url_query( return self.url_result(smuggle_url(update_url_query(

3
youtube_dl/extractor/funnyordie.py
View File

@ -58,8 +58,7 @@ class FunnyOrDieIE(InfoExtractor):
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False) m3u8_id='hls', fatal=False)
source_formats = list(filter( source_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('vcodec') != 'none', m3u8_formats))
m3u8_formats))
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)] bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
bitrates.sort() bitrates.sort()

3
youtube_dl/extractor/gamespot.py
View File

@ -78,8 +78,7 @@ class GameSpotIE(OnceIE):
if m3u8_formats: if m3u8_formats:
self._sort_formats(m3u8_formats) self._sort_formats(m3u8_formats)
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('vcodec') != 'none', m3u8_formats))
m3u8_formats))
if len(qualities) == len(m3u8_formats): if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats): for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy() f = m3u8_format.copy()

86
youtube_dl/extractor/generic.py
View File

@ -85,6 +85,9 @@ from .ustream import UstreamIE
from .openload import OpenloadIE from .openload import OpenloadIE
from .videopress import VideoPressIE from .videopress import VideoPressIE
from .rutube import RutubeIE from .rutube import RutubeIE
from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -429,6 +432,22 @@ class GenericIE(InfoExtractor):
'skip_download': True, # m3u8 download 'skip_download': True, # m3u8 download
}, },
}, },
{
# Brightcove video in <iframe>
'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
'md5': '36d74ef5e37c8b4a2ce92880d208b968',
'info_dict': {
'id': '5360463607001',
'ext': 'mp4',
'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼（Zade Dirani）在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》（HEARTBEAT），为受到六年冲突影响的叙利亚儿童发出强烈呐喊，呼吁世界做出共同努力，使叙利亚儿童重新获得享有正常童年生活的权利。',
'uploader': 'United Nations',
'uploader_id': '1362235914001',
'timestamp': 1489593889,
'upload_date': '20170315',
},
'add_ie': ['BrightcoveLegacy'],
},
{ {
# Brightcove with alternative playerID key # Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html', 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
@ -1410,6 +1429,22 @@ class GenericIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, },
{
# Brightcove embed with whitespace around attribute names
'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
'info_dict': {
'id': '3167554373001',
'ext': 'mp4',
'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
'description': 'md5:57bacb0e0f29349de4972bfda3191713',
'uploader_id': '1079349493',
'upload_date': '20140207',
'timestamp': 1391810548,
},
'params': {
'skip_download': True,
},
},
# Another form of arte.tv embed # Another form of arte.tv embed
{ {
'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html', 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
@ -1651,6 +1686,38 @@ class GenericIE(InfoExtractor):
}, },
'add_ie': [SenateISVPIE.ie_key()], 'add_ie': [SenateISVPIE.ie_key()],
}, },
{
# Limelight embeds (1 channel embed + 4 media embeds)
'url': 'http://www.sedona.com/FacilitatorTraining2017',
'info_dict': {
'id': 'FacilitatorTraining2017',
'title': 'Facilitator Training 2017',
},
'playlist_mincount': 5,
},
{
'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
'info_dict': {
'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
'title': 'Standoff with Walnut Creek murder suspect ends',
'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
},
'playlist_mincount': 4,
},
{
# WashingtonPost embed
'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
'info_dict': {
'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
'ext': 'mp4',
'title': "No one has seen the drama series based on Trump's life \u2014 until now",
'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
'timestamp': 1455216756,
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
'add_ie': [WashingtonPostIE.ie_key()],
},
# { # {
# # TODO: find another test # # TODO: find another test
# # http://schema.org/VideoObject # # http://schema.org/VideoObject
@ -1693,7 +1760,7 @@ class GenericIE(InfoExtractor):
continue continue
entries.append({ entries.append({
'_type': 'url', '_type': 'url_transparent',
'url': next_url, 'url': next_url,
'title': it.find('title').text, 'title': it.find('title').text,
}) })
@ -2483,6 +2550,11 @@ class GenericIE(InfoExtractor):
return self.url_result(piksel_url, PikselIE.ie_key()) return self.url_result(piksel_url, PikselIE.ie_key())
# Look for Limelight embeds # Look for Limelight embeds
limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
if limelight_urls:
return self.playlist_result(
limelight_urls, video_id, video_title, video_description)
mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage) mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
if mobj: if mobj:
lm = { lm = {
@ -2506,6 +2578,12 @@ class GenericIE(InfoExtractor):
'limelight:media:%s' % mobj.group('id'), 'limelight:media:%s' % mobj.group('id'),
{'source_url': url}), 'LimelightMedia', mobj.group('id')) {'source_url': url}), 'LimelightMedia', mobj.group('id'))
# Look for Anvato embeds
anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
if anvato_urls:
return self.playlist_result(
anvato_urls, video_id, video_title, video_description)
# Look for AdobeTVVideo embeds # Look for AdobeTVVideo embeds
mobj = re.search( mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
@ -2623,6 +2701,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches( return self.playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key()) rutube_urls, ie=RutubeIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
# Looking for http://schema.org/VideoObject # Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld( json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject') webpage, video_id, default={}, expected_type='VideoObject')

49
youtube_dl/extractor/go.py
View File

@ -36,22 +36,26 @@ class GoIE(AdobePassIE):
'requestor_id': 'DisneyXD', 'requestor_id': 'DisneyXD',
} }
} }
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys()) _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_TESTS = [{ _TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx', 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': { 'info_dict': {
'id': '0_g86w5onx', 'id': 'VDKA3807643',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Sneak Peek: Language Arts', 'title': 'The Traitor in the White House',
'description': 'md5:7dcdab3b2d17e5217c953256af964e9c', 'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
}, { }, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601', 'url': 'http://watchdisneyxd.go.com/doraemon',
'only_matching': True, 'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, { }, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding', 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True, 'only_matching': True,
@ -60,19 +64,36 @@ class GoIE(AdobePassIE):
'only_matching': True, 'only_matching': True,
}] }]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id = video_id if video_id != '-1' else show_id
return self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
display_id)['video']
def _real_extract(self, url): def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups() sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
if not video_id: if not video_id:
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._search_regex( video_id = self._search_regex(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'" # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id') r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None)
site_info = self._SITE_INFO[sub_domain] if not video_id:
brand = site_info['brand'] # show extraction works for Disney, DisneyJunior and DisneyXD
video_data = self._download_json( # ABC and Freeform has different layout
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id), show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
video_id)['video'][0] videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title'] title = video_data['title']
formats = [] formats = []
@ -105,7 +126,7 @@ class GoIE(AdobePassIE):
self._initialize_geo_bypass(['US']) self._initialize_geo_bypass(['US'])
entitlement = self._download_json( entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json', 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers()) video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', []) errors = entitlement.get('errors', {}).get('errors', [])
if errors: if errors:
for error in errors: for error in errors:

38
youtube_dl/extractor/go90.py
View File

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
) )
@ -18,7 +19,7 @@ class Go90IE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '84BUqjLpf9D', 'id': '84BUqjLpf9D',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Inside The Utah Coalition Against Pornography Convention', 'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention',
'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.', 'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.',
'timestamp': 1491868800, 'timestamp': 1491868800,
'upload_date': '20170411', 'upload_date': '20170411',
@ -32,11 +33,28 @@ class Go90IE(InfoExtractor):
video_id, headers={ video_id, headers={
'Content-Type': 'application/json; charset=utf-8', 'Content-Type': 'application/json; charset=utf-8',
}, data=b'{"client":"web","device_type":"pc"}') }, data=b'{"client":"web","device_type":"pc"}')
title = video_data['title']
main_video_asset = video_data['main_video_asset'] main_video_asset = video_data['main_video_asset']
episode_number = int_or_none(video_data.get('episode_number'))
series = None
season = None
season_id = None
season_number = None
for metadata in video_data.get('__children', {}).get('Item', {}).values():
if metadata.get('type') == 'show':
series = metadata.get('title')
elif metadata.get('type') == 'season':
season = metadata.get('title')
season_id = metadata.get('id')
season_number = int_or_none(metadata.get('season_number'))
title = episode = video_data.get('title') or series
if series and series != title:
title = '%s - %s' % (series, title)
thumbnails = [] thumbnails = []
formats = [] formats = []
subtitles = {}
for asset in video_data.get('assets'): for asset in video_data.get('assets'):
if asset.get('id') == main_video_asset: if asset.get('id') == main_video_asset:
for source in asset.get('sources', []): for source in asset.get('sources', []):
@ -70,6 +88,15 @@ class Go90IE(InfoExtractor):
'height': int_or_none(source.get('height')), 'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('bitrate')), 'tbr': int_or_none(source.get('bitrate')),
}) })
for caption in asset.get('caption_metadata', []):
caption_url = caption.get('source_url')
if not caption_url:
continue
subtitles.setdefault(caption.get('language', 'en'), []).append({
'url': caption_url,
'ext': determine_ext(caption_url, 'vtt'),
})
elif asset.get('type') == 'image': elif asset.get('type') == 'image':
asset_location = asset.get('location') asset_location = asset.get('location')
if not asset_location: if not asset_location:
@ -89,4 +116,11 @@ class Go90IE(InfoExtractor):
'description': video_data.get('short_description'), 'description': video_data.get('short_description'),
'like_count': int_or_none(video_data.get('like_count')), 'like_count': int_or_none(video_data.get('like_count')),
'timestamp': parse_iso8601(video_data.get('released_at')), 'timestamp': parse_iso8601(video_data.get('released_at')),
'series': series,
'episode': episode,
'season': season,
'season_id': season_id,
'season_number': season_number,
'episode_number': episode_number,
'subtitles': subtitles,
} }

4
youtube_dl/extractor/infoq.py
View File

@ -87,8 +87,8 @@ class InfoQIE(BokeCCBaseIE):
def _extract_http_audio(self, webpage, video_id): def _extract_http_audio(self, webpage, video_id):
fields = self._hidden_inputs(webpage) fields = self._hidden_inputs(webpage)
http_audio_url = fields['filename'] http_audio_url = fields.get('filename')
if http_audio_url is None: if not http_audio_url:
return [] return []
cookies_header = {'Cookie': self._extract_cookies(webpage)} cookies_header = {'Cookie': self._extract_cookies(webpage)}

8
youtube_dl/extractor/instagram.py
View File

@ -112,7 +112,8 @@ class InstagramIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
(video_url, description, thumbnail, timestamp, uploader, (video_url, description, thumbnail, timestamp, uploader,
uploader_id, like_count, comment_count, height, width) = [None] * 10 uploader_id, like_count, comment_count, comments, height,
width) = [None] * 11
shared_data = self._parse_json( shared_data = self._parse_json(
self._search_regex( self._search_regex(
@ -121,7 +122,10 @@ class InstagramIE(InfoExtractor):
video_id, fatal=False) video_id, fatal=False)
if shared_data: if shared_data:
media = try_get( media = try_get(
shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict) shared_data,
(lambda x: x['entry_data']['PostPage'][0]['graphql']['shortcode_media'],
lambda x: x['entry_data']['PostPage'][0]['media']),
dict)
if media: if media:
video_url = media.get('video_url') video_url = media.get('video_url')
height = int_or_none(media.get('dimensions', {}).get('height')) height = int_or_none(media.get('dimensions', {}).get('height'))

26
youtube_dl/extractor/iqiyi.py
View File

@ -189,7 +189,11 @@ class IqiyiIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://yule.iqiyi.com/pcb.html', 'url': 'http://yule.iqiyi.com/pcb.html',
'only_matching': True, 'info_dict': {
'id': '4a0af228fddb55ec96398a364248ed7f',
'ext': 'mp4',
'title': '第2017-04-21期 女艺人频遭极端粉丝骚扰',
},
}, { }, {
# VIP-only video. The first 2 parts (6 minutes) are available without login # VIP-only video. The first 2 parts (6 minutes) are available without login
# MD5 sums omitted as values are different on Travis CI and my machine # MD5 sums omitted as values are different on Travis CI and my machine
@ -337,15 +341,18 @@ class IqiyiIE(InfoExtractor):
url, 'temp_id', note='download video page') url, 'temp_id', note='download video page')
# There's no simple way to determine whether an URL is a playlist or not # There's no simple way to determine whether an URL is a playlist or not
# So detect it # Sometimes there are playlist links in individual videos, so treat it
playlist_result = self._extract_playlist(webpage) # as a single video first
if playlist_result:
return playlist_result
tvid = self._search_regex( tvid = self._search_regex(
r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid') r'data-(?:player|shareplattrigger)-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid', default=None)
if tvid is None:
playlist_result = self._extract_playlist(webpage)
if playlist_result:
return playlist_result
raise ExtractorError('Can\'t find any video')
video_id = self._search_regex( video_id = self._search_regex(
r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id') r'data-(?:player|shareplattrigger)-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
formats = [] formats = []
for _ in range(5): for _ in range(5):
@ -377,7 +384,8 @@ class IqiyiIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
title = (get_element_by_id('widget-videotitle', webpage) or title = (get_element_by_id('widget-videotitle', webpage) or
clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage))) clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage)) or
self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
return { return {
'id': video_id, 'id': video_id,

28
youtube_dl/extractor/itv.py
View File

@ -116,13 +116,25 @@ class ITVIE(InfoExtractor):
if not play_path: if not play_path:
continue continue
tbr = int_or_none(media_file.get('bitrate'), 1000) tbr = int_or_none(media_file.get('bitrate'), 1000)
formats.append({ f = {
'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''), 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
'url': rtmp_url,
'play_path': play_path, 'play_path': play_path,
# Providing this swfVfy allows to avoid truncated downloads
'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
'page_url': url,
'tbr': tbr, 'tbr': tbr,
'ext': 'flv', 'ext': 'flv',
}) }
app = self._search_regex(
'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
if app:
f.update({
'url': rtmp_url.split('?', 1)[0],
'app': app,
})
else:
f['url'] = rtmp_url
formats.append(f)
ios_playlist_url = params.get('data-video-playlist') ios_playlist_url = params.get('data-video-playlist')
hmac = params.get('data-video-hmac') hmac = params.get('data-video-hmac')
@ -172,7 +184,9 @@ class ITVIE(InfoExtractor):
href = ios_base_url + href href = ios_base_url + href
ext = determine_ext(href) ext = determine_ext(href)
if ext == 'm3u8': if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(href, video_id, 'mp4', m3u8_id='hls', fatal=False)) formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else: else:
formats.append({ formats.append({
'url': href, 'url': href,
@ -189,7 +203,8 @@ class ITVIE(InfoExtractor):
'ext': 'ttml' if ext == 'xml' else ext, 'ext': 'ttml' if ext == 'xml' else ext,
}) })
return { info = self._search_json_ld(webpage, video_id, default={})
info.update({
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
@ -198,4 +213,5 @@ class ITVIE(InfoExtractor):
'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')), 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
'series': xpath_text(playlist, 'ProgrammeTitle'), 'series': xpath_text(playlist, 'ProgrammeTitle'),
'duartion': parse_duration(xpath_text(playlist, 'Duration')), 'duartion': parse_duration(xpath_text(playlist, 'Duration')),
} })
return info

103
youtube_dl/extractor/leeco.py
View File

@ -23,7 +23,6 @@ from ..utils import (
str_or_none, str_or_none,
url_basename, url_basename,
urshift, urshift,
update_url_query,
) )
@ -51,7 +50,7 @@ class LeIE(InfoExtractor):
'id': '1415246', 'id': '1415246',
'ext': 'mp4', 'ext': 'mp4',
'title': '美人天下01', 'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda', 'description': 'md5:28942e650e82ed4fcc8e4de919ee854d',
}, },
'params': { 'params': {
'hls_prefer_native': True, 'hls_prefer_native': True,
@ -69,7 +68,6 @@ class LeIE(InfoExtractor):
'params': { 'params': {
'hls_prefer_native': True, 'hls_prefer_native': True,
}, },
'skip': 'Only available in China',
}, { }, {
'url': 'http://sports.le.com/video/25737697.html', 'url': 'http://sports.le.com/video/25737697.html',
'only_matching': True, 'only_matching': True,
@ -81,7 +79,7 @@ class LeIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
# ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf # ror() and calc_time_key() are reversed from a embedded swf file in LetvPlayer.swf
def ror(self, param1, param2): def ror(self, param1, param2):
_loc3_ = 0 _loc3_ = 0
while _loc3_ < param2: while _loc3_ < param2:
@ -90,15 +88,8 @@ class LeIE(InfoExtractor):
return param1 return param1
def calc_time_key(self, param1): def calc_time_key(self, param1):
_loc2_ = 773625421 _loc2_ = 185025305
_loc3_ = self.ror(param1, _loc2_ % 13) return self.ror(param1, _loc2_ % 17) ^ _loc2_
_loc3_ = _loc3_ ^ _loc2_
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# reversed from http://jstatic.letvcdn.com/sdk/player.js
def get_mms_key(self, time):
return self.ror(time, 8) ^ 185025305
# see M3U8Encryption class in KLetvPlayer.swf # see M3U8Encryption class in KLetvPlayer.swf
@staticmethod @staticmethod
@ -122,7 +113,7 @@ class LeIE(InfoExtractor):
def _check_errors(self, play_json): def _check_errors(self, play_json):
# Check for errors # Check for errors
playstatus = play_json['playstatus'] playstatus = play_json['msgs']['playstatus']
if playstatus['status'] == 0: if playstatus['status'] == 0:
flag = playstatus['flag'] flag = playstatus['flag']
if flag == 1: if flag == 1:
@ -134,58 +125,31 @@ class LeIE(InfoExtractor):
media_id = self._match_id(url) media_id = self._match_id(url)
page = self._download_webpage(url, media_id) page = self._download_webpage(url, media_id)
play_json_h5 = self._download_json(
'http://api.le.com/mms/out/video/playJsonH5',
media_id, 'Downloading html5 playJson data', query={
'id': media_id,
'platid': 3,
'splatid': 304,
'format': 1,
'tkey': self.get_mms_key(int(time.time())),
'domain': 'www.le.com',
'tss': 'no',
},
headers=self.geo_verification_headers())
self._check_errors(play_json_h5)
play_json_flash = self._download_json( play_json_flash = self._download_json(
'http://api.le.com/mms/out/video/playJson', 'http://player-pc.le.com/mms/out/video/playJson',
media_id, 'Downloading flash playJson data', query={ media_id, 'Downloading flash playJson data', query={
'id': media_id, 'id': media_id,
'platid': 1, 'platid': 1,
'splatid': 101, 'splatid': 101,
'format': 1, 'format': 1,
'source': 1000,
'tkey': self.calc_time_key(int(time.time())), 'tkey': self.calc_time_key(int(time.time())),
'domain': 'www.le.com', 'domain': 'www.le.com',
'region': 'cn',
}, },
headers=self.geo_verification_headers()) headers=self.geo_verification_headers())
self._check_errors(play_json_flash) self._check_errors(play_json_flash)
def get_h5_urls(media_url, format_id):
location = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id, query={
'format': 1,
'expect': 3,
'tss': 'no',
})['location']
return {
'http': update_url_query(location, {'tss': 'no'}),
'hls': update_url_query(location, {'tss': 'ios'}),
}
def get_flash_urls(media_url, format_id): def get_flash_urls(media_url, format_id):
media_url += '&' + compat_urllib_parse_urlencode({
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
})
nodes_data = self._download_json( nodes_data = self._download_json(
media_url, media_id, media_url, media_id,
'Download JSON metadata for format %s' % format_id) 'Download JSON metadata for format %s' % format_id,
query={
'm3v': 1,
'format': 1,
'expect': 3,
'tss': 'ios',
})
req = self._request_webpage( req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id, nodes_data['nodelist'][0]['location'], media_id,
@ -199,29 +163,28 @@ class LeIE(InfoExtractor):
extracted_formats = [] extracted_formats = []
formats = [] formats = []
for play_json, get_urls in ((play_json_h5, get_h5_urls), (play_json_flash, get_flash_urls)): playurl = play_json_flash['msgs']['playurl']
playurl = play_json['playurl'] play_domain = playurl['domain'][0]
play_domain = playurl['domain'][0]
for format_id, format_data in playurl.get('dispatch', []).items(): for format_id, format_data in playurl.get('dispatch', []).items():
if format_id in extracted_formats: if format_id in extracted_formats:
continue continue
extracted_formats.append(format_id) extracted_formats.append(format_id)
media_url = play_domain + format_data[0] media_url = play_domain + format_data[0]
for protocol, format_url in get_urls(media_url, format_id).items(): for protocol, format_url in get_flash_urls(media_url, format_id).items():
f = { f = {
'url': format_url, 'url': format_url,
'ext': determine_ext(format_data[1]), 'ext': determine_ext(format_data[1]),
'format_id': '%s-%s' % (protocol, format_id), 'format_id': '%s-%s' % (protocol, format_id),
'protocol': 'm3u8_native' if protocol == 'hls' else 'http', 'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
'quality': int_or_none(format_id), 'quality': int_or_none(format_id),
} }
if format_id[-1:] == 'p': if format_id[-1:] == 'p':
f['height'] = int_or_none(format_id[:-1]) f['height'] = int_or_none(format_id[:-1])
formats.append(f) formats.append(f)
self._sort_formats(formats, ('height', 'quality', 'format_id')) self._sort_formats(formats, ('height', 'quality', 'format_id'))
publish_time = parse_iso8601(self._html_search_regex( publish_time = parse_iso8601(self._html_search_regex(

2
youtube_dl/extractor/lego.py
View File

@ -86,7 +86,7 @@ class LEGOIE(InfoExtractor):
formats = self._extract_akamai_formats( formats = self._extract_akamai_formats(
'%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id) '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none',
formats)) formats))
if len(m3u8_formats) == len(self._BITRATES): if len(m3u8_formats) == len(self._BITRATES):
self._sort_formats(m3u8_formats) self._sort_formats(m3u8_formats)

37
youtube_dl/extractor/limelight.py
View File

@ -9,6 +9,7 @@ from ..utils import (
determine_ext, determine_ext,
float_or_none, float_or_none,
int_or_none, int_or_none,
smuggle_url,
unsmuggle_url, unsmuggle_url,
ExtractorError, ExtractorError,
) )
@ -18,6 +19,42 @@ class LimelightBaseIE(InfoExtractor):
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
_API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
@classmethod
def _extract_urls(cls, webpage, source_url):
lm = {
'Media': 'media',
'Channel': 'channel',
'ChannelList': 'channel_list',
}
entries = []
for kind, video_id in re.findall(
r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})',
webpage):
entries.append(cls.url_result(
smuggle_url(
'limelight:%s:%s' % (lm[kind], video_id),
{'source_url': source_url}),
'Limelight%s' % kind, video_id))
for mobj in re.finditer(
# As per [1] class attribute should be exactly equal to
# LimelightEmbeddedPlayerFlash but numerous examples seen
# that don't exactly match it (e.g. [2]).
# 1. http://support.3playmedia.com/hc/en-us/articles/227732408-Limelight-Embedding-the-Captions-Plugin-with-the-Limelight-Player-on-Your-Webpage
# 2. http://www.sedona.com/FacilitatorTraining2017
r'''(?sx)
<object[^>]+class=(["\'])(?:(?!\1).)*\bLimelightEmbeddedPlayerFlash\b(?:(?!\1).)*\1[^>]*>.*?
<param[^>]+
name=(["\'])flashVars\2[^>]+
value=(["\'])(?:(?!\3).)*(?P<kind>media|channel(?:List)?)Id=(?P<id>[a-z0-9]{32})
''', webpage):
kind, video_id = mobj.group('kind'), mobj.group('id')
entries.append(cls.url_result(
smuggle_url(
'limelight:%s:%s' % (kind, video_id),
{'source_url': source_url}),
'Limelight%s' % kind.capitalize(), video_id))
return entries
def _call_playlist_service(self, item_id, method, fatal=True, referer=None): def _call_playlist_service(self, item_id, method, fatal=True, referer=None):
headers = {} headers = {}
if referer: if referer:

97
youtube_dl/extractor/noovo.py Normal file
View File

@ -0,0 +1,97 @@
# coding: utf-8
from __future__ import unicode_literals
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
smuggle_url,
try_get,
)
class NoovoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
_TESTS = [{
# clip
'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
'info_dict': {
'id': '5386045029001',
'ext': 'mp4',
'title': 'Chrysler Imperial',
'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
'timestamp': 1491399228,
'upload_date': '20170405',
'uploader_id': '618566855001',
'creator': 'vtele',
'view_count': int,
'series': 'RPM+',
},
'params': {
'skip_download': True,
},
}, {
# episode
'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
'info_dict': {
'id': '5395865725001',
'title': 'Épisode 13 : Les retrouvailles',
'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
'ext': 'mp4',
'timestamp': 1492019320,
'upload_date': '20170412',
'uploader_id': '618566855001',
'creator': 'vtele',
'view_count': int,
'series': "L'amour est dans le pré",
'season_number': 5,
'episode': 'Épisode 13',
'episode_number': 13,
},
'params': {
'skip_download': True,
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
video_id)['data']
content = try_get(data, lambda x: x['contents'][0])
brightcove_id = data.get('brightcoveId') or content['brightcoveId']
series = try_get(
data, (
lambda x: x['show']['title'],
lambda x: x['season']['show']['title']),
compat_str)
episode = None
og = data.get('og')
if isinstance(og, dict) and og.get('type') == 'video.episode':
episode = og.get('title')
video = content or data
return {
'_type': 'url_transparent',
'ie_key': BrightcoveNewIE.ie_key(),
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
{'geo_countries': ['CA']}),
'id': brightcove_id,
'title': video.get('title'),
'creator': video.get('source'),
'view_count': int_or_none(video.get('viewsCount')),
'series': series,
'season_number': int_or_none(try_get(
data, lambda x: x['season']['seasonNumber'])),
'episode': episode,
'episode_number': int_or_none(data.get('episodeNumber')),
}

2
youtube_dl/extractor/nowness.py
View File

@ -28,7 +28,7 @@ class NownessBaseIE(InfoExtractor):
bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code) bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
if bc_url: if bc_url:
return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
bc_url = BrightcoveNewIE._extract_url(player_code) bc_url = BrightcoveNewIE._extract_url(self, player_code)
if bc_url: if bc_url:
return self.url_result(bc_url, BrightcoveNewIE.ie_key()) return self.url_result(bc_url, BrightcoveNewIE.ie_key())
raise ExtractorError('Could not find player definition') raise ExtractorError('Could not find player definition')

32
youtube_dl/extractor/odnoklassniki.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_etree_fromstring,
compat_parse_qs, compat_parse_qs,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
@ -37,7 +38,7 @@ class OdnoklassnikiIE(InfoExtractor):
}, { }, {
# metadataUrl # metadataUrl
'url': 'http://ok.ru/video/63567059965189-0?fromTime=5', 'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
'md5': '9676cf86eff5391d35dea675d224e131', 'md5': '6ff470ea2dd51d5d18c295a355b0b6bc',
'info_dict': { 'info_dict': {
'id': '63567059965189-0', 'id': '63567059965189-0',
'ext': 'mp4', 'ext': 'mp4',
@ -53,7 +54,7 @@ class OdnoklassnikiIE(InfoExtractor):
}, { }, {
# YouTube embed (metadataUrl, provider == USER_YOUTUBE) # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
'url': 'http://ok.ru/video/64211978996595-1', 'url': 'http://ok.ru/video/64211978996595-1',
'md5': '5d7475d428845cd2e13bae6f1a992278', 'md5': '2f206894ffb5dbfcce2c5a14b909eea5',
'info_dict': { 'info_dict': {
'id': '64211978996595-1', 'id': '64211978996595-1',
'ext': 'mp4', 'ext': 'mp4',
@ -61,8 +62,8 @@ class OdnoklassnikiIE(InfoExtractor):
'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0', 'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
'duration': 440, 'duration': 440,
'upload_date': '20150826', 'upload_date': '20150826',
'uploader_id': '750099571', 'uploader_id': 'tvroscosmos',
'uploader': 'Алина П', 'uploader': 'Телестудия Роскосмоса',
'age_limit': 0, 'age_limit': 0,
}, },
}, { }, {
@ -81,6 +82,7 @@ class OdnoklassnikiIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Video has not been found',
}, { }, {
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', 'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
'only_matching': True, 'only_matching': True,
@ -176,14 +178,32 @@ class OdnoklassnikiIE(InfoExtractor):
}) })
return info return info
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd', 'full')) quality = qualities(('4', '0', '1', '2', '3', '5'))
formats = [{ formats = [{
'url': f['url'], 'url': f['url'],
'ext': 'mp4', 'ext': 'mp4',
'format_id': f['name'], 'format_id': f['name'],
'quality': quality(f['name']),
} for f in metadata['videos']] } for f in metadata['videos']]
m3u8_url = metadata.get('hlsManifestUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
dash_manifest = metadata.get('metadataEmbedded')
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(dash_manifest), 'mpd'))
for fmt in formats:
fmt_type = self._search_regex(
r'\btype[/=](\d)', fmt['url'],
'format type', default=None)
if fmt_type:
fmt['quality'] = quality(fmt_type)
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats info['formats'] = formats

19
youtube_dl/extractor/pbs.py
View File

@ -8,6 +8,7 @@ from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
int_or_none, int_or_none,
float_or_none,
js_to_json, js_to_json,
strip_jsonp, strip_jsonp,
strip_or_none, strip_or_none,
@ -464,6 +465,7 @@ class PBSIE(InfoExtractor):
redirects.append(redirect) redirects.append(redirect)
redirect_urls.add(redirect_url) redirect_urls.add(redirect_url)
chapters = []
# Player pages may also serve different qualities # Player pages may also serve different qualities
for page in ('widget/partnerplayer', 'portalplayer'): for page in ('widget/partnerplayer', 'portalplayer'):
player = self._download_webpage( player = self._download_webpage(
@ -479,6 +481,20 @@ class PBSIE(InfoExtractor):
extract_redirect_urls(video_info) extract_redirect_urls(video_info)
if not info: if not info:
info = video_info info = video_info
if not chapters:
for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
if not chapter:
continue
start_time = float_or_none(chapter.get('start_time'), 1000)
duration = float_or_none(chapter.get('duration'), 1000)
if start_time is None or duration is None:
continue
chapters.append({
'start_time': start_time,
'end_time': start_time + duration,
'title': chapter.get('title'),
})
formats = [] formats = []
http_url = None http_url = None
@ -515,7 +531,7 @@ class PBSIE(InfoExtractor):
http_url = format_url http_url = format_url
self._remove_duplicate_formats(formats) self._remove_duplicate_formats(formats)
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
formats)) formats))
if http_url: if http_url:
for m3u8_format in m3u8_formats: for m3u8_format in m3u8_formats:
@ -588,4 +604,5 @@ class PBSIE(InfoExtractor):
'upload_date': upload_date, 'upload_date': upload_date,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'chapters': chapters,
} }

32
youtube_dl/extractor/porn91.py
View File

@ -1,10 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
)
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
@ -19,7 +15,7 @@ class Porn91IE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134', 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
'md5': '6df8f6d028bc8b14f5dbd73af742fb20', 'md5': '7fcdb5349354f40d41689bd0fa8db05a',
'info_dict': { 'info_dict': {
'id': '7e42283b4f5ab36da134', 'id': '7e42283b4f5ab36da134',
'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！', 'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！',
@ -43,24 +39,7 @@ class Porn91IE(InfoExtractor):
r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title') r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
title = title.replace('\n', '') title = title.replace('\n', '')
# get real url info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
file_id = self._search_regex(
r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
sec_code = self._search_regex(
r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
max_vid = self._search_regex(
r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
url_params = compat_urllib_parse_urlencode({
'VID': file_id,
'mp4': '1',
'seccode': sec_code,
'max_vid': max_vid,
})
info_cn = self._download_webpage(
'http://91porn.com/getfile.php?' + url_params, video_id,
'Downloading real video url')
video_url = compat_urllib_parse_unquote(self._search_regex(
r'file=([^&]+)&', info_cn, 'url'))
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False)) r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
@ -68,11 +47,12 @@ class Porn91IE(InfoExtractor):
comment_count = int_or_none(self._search_regex( comment_count = int_or_none(self._search_regex(
r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False)) r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
return { info_dict.update({
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url,
'duration': duration, 'duration': duration,
'comment_count': comment_count, 'comment_count': comment_count,
'age_limit': self._rta_search(webpage), 'age_limit': self._rta_search(webpage),
} })
return info_dict

3
youtube_dl/extractor/r7.py
View File

@ -62,8 +62,7 @@ class R7IE(InfoExtractor):
# m3u8 format always matches the http format, let's copy metadata from # m3u8 format always matches the http format, let's copy metadata from
# one to another # one to another
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('vcodec') != 'none', formats))
formats))
if len(m3u8_formats) == 1: if len(m3u8_formats) == 1:
f_copy = m3u8_formats[0].copy() f_copy = m3u8_formats[0].copy()
f_copy.update(f) f_copy.update(f)

6
youtube_dl/extractor/streamable.py
View File

@ -12,7 +12,7 @@ from ..utils import (
class StreamableIE(InfoExtractor): class StreamableIE(InfoExtractor):
_VALID_URL = r'https?://streamable\.com/(?:e/)?(?P<id>\w+)' _VALID_URL = r'https?://streamable\.com/(?:[es]/)?(?P<id>\w+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://streamable.com/dnd1', 'url': 'https://streamable.com/dnd1',
@ -47,6 +47,10 @@ class StreamableIE(InfoExtractor):
{ {
'url': 'https://streamable.com/e/dnd1', 'url': 'https://streamable.com/e/dnd1',
'only_matching': True, 'only_matching': True,
},
{
'url': 'https://streamable.com/s/okkqk/drxjds',
'only_matching': True,
} }
] ]

64
youtube_dl/extractor/streamango.py Normal file
View File

@ -0,0 +1,64 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
)
class StreamangoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
'md5': 'e992787515a182f55e38fc97588d802a',
'info_dict': {
'id': 'clapasobsptpkdfe',
'ext': 'mp4',
'title': '20170315_150006.mp4',
}
}, {
'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
formats = []
for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
video = self._parse_json(
format_, video_id, transform_source=js_to_json, fatal=False)
if not video:
continue
src = video.get('src')
if not src:
continue
ext = determine_ext(src, default_ext=None)
if video.get('type') == 'application/dash+xml' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
src, video_id, mpd_id='dash', fatal=False))
else:
formats.append({
'url': src,
'ext': ext or 'mp4',
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'tbr': int_or_none(video.get('bitrate')),
})
self._sort_formats(formats)
return {
'id': video_id,
'url': url,
'title': title,
'formats': formats,
}

2
youtube_dl/extractor/ted.py
View File

@ -210,7 +210,7 @@ class TEDIE(InfoExtractor):
resources.get('stream'), video_name, 'mp4', m3u8_id=format_id, fatal=False)) resources.get('stream'), video_name, 'mp4', m3u8_id=format_id, fatal=False))
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
formats)) formats))
if http_url: if http_url:
for m3u8_format in m3u8_formats: for m3u8_format in m3u8_formats:

3
youtube_dl/extractor/tvp.py
View File

@ -150,8 +150,7 @@ class TVPEmbedIE(InfoExtractor):
'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
self._sort_formats(m3u8_formats) self._sort_formats(m3u8_formats)
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('vcodec') != 'none', m3u8_formats))
m3u8_formats))
formats.extend(m3u8_formats) formats.extend(m3u8_formats)
for i, m3u8_format in enumerate(m3u8_formats, 2): for i, m3u8_format in enumerate(m3u8_formats, 2):
http_url = '%s-%d.mp4' % (video_url_base, i) http_url = '%s-%d.mp4' % (video_url_base, i)

35
youtube_dl/extractor/tvplayer.py
View File

@ -2,9 +2,13 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_HTTPError from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import ( from ..utils import (
extract_attributes, extract_attributes,
try_get,
urlencode_postdata, urlencode_postdata,
ExtractorError, ExtractorError,
) )
@ -34,25 +38,32 @@ class TVPlayerIE(InfoExtractor):
webpage, 'channel element')) webpage, 'channel element'))
title = current_channel['data-name'] title = current_channel['data-name']
resource_id = self._search_regex( resource_id = current_channel['data-id']
r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id')
platform = self._search_regex(
r'platform\s*=\s*"([^"]+)"', webpage, 'platform')
token = self._search_regex( token = self._search_regex(
r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null') r'data-token=(["\'])(?P<token>(?!\1).+)\1', webpage,
validate = self._search_regex( 'token', group='token')
r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null')
context = self._download_json(
'https://tvplayer.com/watch/context', display_id,
'Downloading JSON context', query={
'resource': resource_id,
'nonce': token,
})
validate = context['validate']
platform = try_get(
context, lambda x: x['platform']['key'], compat_str) or 'firefox'
try: try:
response = self._download_json( response = self._download_json(
'http://api.tvplayer.com/api/v2/stream/live', 'http://api.tvplayer.com/api/v2/stream/live',
resource_id, headers={ display_id, 'Downloading JSON stream', headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
}, data=urlencode_postdata({ }, data=urlencode_postdata({
'id': resource_id,
'service': 1, 'service': 1,
'platform': platform, 'platform': platform,
'id': resource_id,
'token': token,
'validate': validate, 'validate': validate,
}))['tvplayer']['response'] }))['tvplayer']['response']
except ExtractorError as e: except ExtractorError as e:
@ -63,7 +74,7 @@ class TVPlayerIE(InfoExtractor):
'%s said: %s' % (self.IE_NAME, response['error']), expected=True) '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
raise raise
formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4') formats = self._extract_m3u8_formats(response['stream'], display_id, 'mp4')
self._sort_formats(formats) self._sort_formats(formats)
return { return {

17
youtube_dl/extractor/vevo.py
View File

@ -1,6 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
@ -11,7 +12,6 @@ from ..compat import (
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
sanitized_Request,
parse_iso8601, parse_iso8601,
) )
@ -154,19 +154,24 @@ class VevoIE(VevoBaseIE):
} }
def _initialize_api(self, video_id): def _initialize_api(self, video_id):
req = sanitized_Request(
'http://www.vevo.com/auth', data=b'')
webpage = self._download_webpage( webpage = self._download_webpage(
req, None, 'https://accounts.vevo.com/token', None,
note='Retrieving oauth token', note='Retrieving oauth token',
errnote='Unable to retrieve oauth token') errnote='Unable to retrieve oauth token',
data=json.dumps({
'client_id': 'SPupX1tvqFEopQ1YS6SS',
'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous',
}).encode('utf-8'),
headers={
'Content-Type': 'application/json',
})
if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage): if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
self.raise_geo_restricted( self.raise_geo_restricted(
'%s said: This page is currently unavailable in your region' % self.IE_NAME) '%s said: This page is currently unavailable in your region' % self.IE_NAME)
auth_info = self._parse_json(webpage, video_id) auth_info = self._parse_json(webpage, video_id)
self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token'] self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token']
def _call_api(self, path, *args, **kwargs): def _call_api(self, path, *args, **kwargs):
try: try:

9
youtube_dl/extractor/videopress.py
View File

@ -1,7 +1,6 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import random
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -11,6 +10,7 @@ from ..utils import (
float_or_none, float_or_none,
parse_age_limit, parse_age_limit,
qualities, qualities,
random_birthday,
try_get, try_get,
unified_timestamp, unified_timestamp,
urljoin, urljoin,
@ -47,13 +47,10 @@ class VideoPressIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
query = random_birthday('birth_year', 'birth_month', 'birth_day')
video = self._download_json( video = self._download_json(
'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id, 'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
video_id, query={ video_id, query=query)
'birth_month': random.randint(1, 12),
'birth_day': random.randint(1, 31),
'birth_year': random.randint(1950, 1995),
})
title = video['title'] title = video['title']

7
youtube_dl/extractor/vidio.py
View File

@ -49,8 +49,11 @@ class VidioIE(InfoExtractor):
thumbnail = clip.get('image') thumbnail = clip.get('image')
m3u8_url = m3u8_url or self._search_regex( m3u8_url = m3u8_url or self._search_regex(
r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>.+?)\1', webpage, 'hls url') r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>(?!\1).+)\1',
formats = self._extract_m3u8_formats(m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native') webpage, 'hls url')
formats = self._extract_m3u8_formats(
m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
self._sort_formats(formats)
duration = int_or_none(duration or self._search_regex( duration = int_or_none(duration or self._search_regex(
r'data-video-duration=(["\'])(?P<duartion>\d+)\1', webpage, 'duration')) r'data-video-duration=(["\'])(?P<duartion>\d+)\1', webpage, 'duration'))

11
youtube_dl/extractor/vidzi.py
View File

@ -42,14 +42,15 @@ class VidziIE(InfoExtractor):
title = self._html_search_regex( title = self._html_search_regex(
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
packed_codes = [mobj.group(0) for mobj in re.finditer( codes = [webpage]
PACKED_CODES_RE, webpage)] codes.extend([
for num, pc in enumerate(packed_codes, 1): decode_packed_codes(mobj.group(0)).replace('\\\'', '\'')
code = decode_packed_codes(pc).replace('\\\'', '\'') for mobj in re.finditer(PACKED_CODES_RE, webpage)])
for num, code in enumerate(codes, 1):
jwplayer_data = self._parse_json( jwplayer_data = self._parse_json(
self._search_regex( self._search_regex(
r'setup\(([^)]+)\)', code, 'jwplayer data', r'setup\(([^)]+)\)', code, 'jwplayer data',
default=NO_DEFAULT if num == len(packed_codes) else '{}'), default=NO_DEFAULT if num == len(codes) else '{}'),
video_id, transform_source=js_to_json) video_id, transform_source=js_to_json)
if jwplayer_data: if jwplayer_data:
break break

3
youtube_dl/extractor/viewster.py
View File

@ -176,8 +176,7 @@ class ViewsterIE(InfoExtractor):
if m3u8_formats: if m3u8_formats:
self._sort_formats(m3u8_formats) self._sort_formats(m3u8_formats)
m3u8_formats = list(filter( m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', lambda f: f.get('vcodec') != 'none', m3u8_formats))
m3u8_formats))
if len(qualities) == len(m3u8_formats): if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats): for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy() f = m3u8_format.copy()

6
youtube_dl/extractor/washingtonpost.py
View File

@ -13,6 +13,7 @@ from ..utils import (
class WashingtonPostIE(InfoExtractor): class WashingtonPostIE(InfoExtractor):
IE_NAME = 'washingtonpost' IE_NAME = 'washingtonpost'
_VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/video/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/video/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_EMBED_URL = r'https?://(?:www\.)?washingtonpost\.com/video/c/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_TEST = { _TEST = {
'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d', 'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
'md5': '6f537e1334b714eb15f9563bd4b9cdfa', 'md5': '6f537e1334b714eb15f9563bd4b9cdfa',
@ -27,6 +28,11 @@ class WashingtonPostIE(InfoExtractor):
}, },
} }
@classmethod
def _extract_urls(cls, webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\'](%s)' % cls._EMBED_URL, webpage)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_json( video_data = self._download_json(

52
youtube_dl/extractor/wsj.py
View File

@ -10,12 +10,14 @@ from ..utils import (
class WSJIE(InfoExtractor): class WSJIE(InfoExtractor):
_VALID_URL = r'''(?x)https?:// _VALID_URL = r'''(?x)
(?: (?:
video-api\.wsj\.com/api-video/player/iframe\.html\?guid=| https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
(?:www\.)?wsj\.com/video/[^/]+/ https?://(?:www\.)?wsj\.com/video/[^/]+/|
) wsj:
(?P<id>[a-zA-Z0-9-]+)''' )
(?P<id>[a-fA-F0-9-]{36})
'''
IE_DESC = 'Wall Street Journal' IE_DESC = 'Wall Street Journal'
_TESTS = [{ _TESTS = [{
'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A', 'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
@ -38,12 +40,17 @@ class WSJIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
api_url = ( info = self._download_json(
'http://video-api.wsj.com/api-video/find_all_videos.asp?' 'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
'type=guid&count=1&query=%s&fields=type,hls,videoMP4List,' query={
'thumbnailList,author,description,name,duration,videoURL,' 'type': 'guid',
'titletag,formattedCreationDate,keywords,editor' % video_id) 'count': 1,
info = self._download_json(api_url, video_id)['items'][0] 'query': video_id,
'fields': ','.join((
'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
'description', 'name', 'duration', 'videoURL', 'titletag',
'formattedCreationDate', 'keywords', 'editor')),
})['items'][0]
title = info.get('name', info.get('titletag')) title = info.get('name', info.get('titletag'))
formats = [] formats = []
@ -87,3 +94,24 @@ class WSJIE(InfoExtractor):
'title': title, 'title': title,
'categories': info.get('keywords'), 'categories': info.get('keywords'),
} }
class WSJArticleIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
'info_dict': {
'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
'ext': 'mp4',
'upload_date': '20170221',
'uploader_id': 'ralcaraz',
'title': 'Bao Bao the Panda Leaves for China',
}
}
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
video_id = self._search_regex(
r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id')
return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)

28
youtube_dl/extractor/xfileshare.py
View File

@ -17,24 +17,24 @@ from ..utils import (
class XFileShareIE(InfoExtractor): class XFileShareIE(InfoExtractor):
_SITES = ( _SITES = (
('daclips.in', 'DaClips'), (r'daclips\.(?:in|com)', 'DaClips'),
('filehoot.com', 'FileHoot'), (r'filehoot\.com', 'FileHoot'),
('gorillavid.in', 'GorillaVid'), (r'gorillavid\.(?:in|com)', 'GorillaVid'),
('movpod.in', 'MovPod'), (r'movpod\.in', 'MovPod'),
('powerwatch.pw', 'PowerWatch'), (r'powerwatch\.pw', 'PowerWatch'),
('rapidvideo.ws', 'Rapidvideo.ws'), (r'rapidvideo\.ws', 'Rapidvideo.ws'),
('thevideobee.to', 'TheVideoBee'), (r'thevideobee\.to', 'TheVideoBee'),
('vidto.me', 'Vidto'), (r'vidto\.me', 'Vidto'),
('streamin.to', 'Streamin.To'), (r'streamin\.to', 'Streamin.To'),
('xvidstage.com', 'XVIDSTAGE'), (r'xvidstage\.com', 'XVIDSTAGE'),
('vidabc.com', 'Vid ABC'), (r'vidabc\.com', 'Vid ABC'),
('vidbom.com', 'VidBom'), (r'vidbom\.com', 'VidBom'),
('vidlo.us', 'vidlo'), (r'vidlo\.us', 'vidlo'),
) )
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1]) IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
_VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(re.escape(site) for site in list(zip(*_SITES))[0])) % '|'.join(site for site in list(zip(*_SITES))[0]))
_FILE_NOT_FOUND_REGEXES = ( _FILE_NOT_FOUND_REGEXES = (
r'>(?:404 - )?File Not Found<', r'>(?:404 - )?File Not Found<',

23
youtube_dl/extractor/xtube.py
View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
js_to_json,
orderedSet, orderedSet,
parse_duration, parse_duration,
sanitized_Request, sanitized_Request,
@ -37,6 +38,22 @@ class XTubeIE(InfoExtractor):
'comment_count': int, 'comment_count': int,
'age_limit': 18, 'age_limit': 18,
} }
}, {
# FLV videos with duplicated formats
'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
'md5': 'a406963eb349dd43692ec54631efd88b',
'info_dict': {
'id': '9299752',
'display_id': 'A-Super-Run-Part-1-YT',
'ext': 'flv',
'title': 'A Super Run - Part 1 (YT)',
'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
'uploader': 'tshirtguy59',
'duration': 579,
'view_count': int,
'comment_count': int,
'age_limit': 18,
},
}, { }, {
# new URL schema # new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
@ -68,8 +85,9 @@ class XTubeIE(InfoExtractor):
}) })
sources = self._parse_json(self._search_regex( sources = self._parse_json(self._search_regex(
r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
webpage, 'sources', group='sources'), video_id) webpage, 'sources', group='sources'), video_id,
transform_source=js_to_json)
formats = [] formats = []
for format_id, format_url in sources.items(): for format_id, format_url in sources.items():
@ -78,6 +96,7 @@ class XTubeIE(InfoExtractor):
'format_id': format_id, 'format_id': format_id,
'height': int_or_none(format_id), 'height': int_or_none(format_id),
}) })
self._remove_duplicate_formats(formats)
self._sort_formats(formats) self._sort_formats(formats)
title = self._search_regex( title = self._search_regex(

11
youtube_dl/extractor/xvideos.py
View File

@ -6,8 +6,10 @@ from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote from ..compat import compat_urllib_parse_unquote
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError,
determine_ext, determine_ext,
ExtractorError,
int_or_none,
parse_duration,
) )
@ -20,6 +22,7 @@ class XVideosIE(InfoExtractor):
'id': '4588838', 'id': '4588838',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Biker Takes his Girl', 'title': 'Biker Takes his Girl',
'duration': 108,
'age_limit': 18, 'age_limit': 18,
} }
} }
@ -36,6 +39,11 @@ class XVideosIE(InfoExtractor):
r'<title>(.*?)\s+-\s+XVID', webpage, 'title') r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
video_thumbnail = self._search_regex( video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False) r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
video_duration = int_or_none(self._og_search_property(
'duration', webpage, default=None)) or parse_duration(
self._search_regex(
r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
webpage, 'duration', fatal=False))
formats = [] formats = []
@ -67,6 +75,7 @@ class XVideosIE(InfoExtractor):
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'title': video_title, 'title': video_title,
'duration': video_duration,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'age_limit': 18, 'age_limit': 18,
} }

2
youtube_dl/extractor/yahoo.py
View File

@ -258,7 +258,7 @@ class YahooIE(InfoExtractor):
return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
# Look for Brightcove New Studio embeds # Look for Brightcove New Studio embeds
bc_url = BrightcoveNewIE._extract_url(webpage) bc_url = BrightcoveNewIE._extract_url(self, webpage)
if bc_url: if bc_url:
return self.url_result(bc_url, BrightcoveNewIE.ie_key()) return self.url_result(bc_url, BrightcoveNewIE.ie_key())

3
youtube_dl/extractor/yandexmusic.py
View File

@ -234,7 +234,8 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
'overembed': 'false', 'overembed': 'false',
})['playlist'] })['playlist']
tracks, track_ids = playlist['tracks'], map(compat_str, playlist['trackIds']) tracks = playlist['tracks']
track_ids = [compat_str(track_id) for track_id in playlist['trackIds']]
# tracks dictionary shipped with playlist.jsx API is limited to 150 tracks, # tracks dictionary shipped with playlist.jsx API is limited to 150 tracks,
# missing tracks should be retrieved manually. # missing tracks should be retrieved manually.

5
youtube_dl/extractor/youtube.py
View File

@ -963,7 +963,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_signature_function(self, video_id, player_url, example_sig): def _extract_signature_function(self, video_id, player_url, example_sig):
id_m = re.match( id_m = re.match(
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$', r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
player_url) player_url)
if not id_m: if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url) raise ExtractorError('Cannot identify player %r' % player_url)
@ -1629,7 +1629,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
player_desc = 'flash player %s' % player_version player_desc = 'flash player %s' % player_version
else: else:
player_version = self._search_regex( player_version = self._search_regex(
[r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'], [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
player_url, player_url,
'html5 player', fatal=False) 'html5 player', fatal=False)
player_desc = 'html5 player %s' % player_version player_desc = 'html5 player %s' % player_version

101
youtube_dl/extractor/zaq1.py Normal file
View File

@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_timestamp,
)
class Zaq1IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?zaq1\.pl/video/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://zaq1.pl/video/xev0e',
'md5': '24a5eb3f052e604ae597c4d0d19b351e',
'info_dict': {
'id': 'xev0e',
'title': 'DJ NA WESELE. TANIEC Z FIGURAMI.węgrów/sokołów podlaski/siedlce/mińsk mazowiecki/warszawa',
'description': 'www.facebook.com/weseledjKontakt: 728 448 199 / 505 419 147',
'ext': 'mp4',
'duration': 511,
'timestamp': 1490896361,
'uploader': 'Anonim',
'upload_date': '20170330',
'view_count': int,
}
}, {
# malformed JSON-LD
'url': 'http://zaq1.pl/video/x81vn',
'info_dict': {
'id': 'x81vn',
'title': 'SEKRETNE ŻYCIE WALTERA MITTY',
'ext': 'mp4',
'duration': 6234,
'timestamp': 1493494860,
'uploader': 'Anonim',
'upload_date': '20170429',
'view_count': int,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Failed to parse JSON'],
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'data-video-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'video url', group='url')
info = self._search_json_ld(webpage, video_id, fatal=False)
def extract_data(field, name, fatal=False):
return self._search_regex(
r'data-%s=(["\'])(?P<field>(?:(?!\1).)+)\1' % field,
webpage, field, fatal=fatal, group='field')
if not info.get('title'):
info['title'] = extract_data('file-name', 'title', fatal=True)
if not info.get('duration'):
info['duration'] = int_or_none(extract_data('duration', 'duration'))
if not info.get('thumbnail'):
info['thumbnail'] = extract_data('photo-url', 'thumbnail')
if not info.get('timestamp'):
info['timestamp'] = unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp'))
if not info.get('interactionCount'):
info['view_count'] = int_or_none(self._html_search_meta(
'interactionCount', webpage, 'view count'))
uploader = self._html_search_regex(
r'Wideo dodał:\s*<a[^>]*>([^<]+)</a>', webpage, 'uploader',
fatal=False)
width = int_or_none(self._html_search_meta(
'width', webpage, fatal=False))
height = int_or_none(self._html_search_meta(
'height', webpage, fatal=False))
info.update({
'id': video_id,
'formats': [{
'url': video_url,
'width': width,
'height': height,
'http_headers': {
'Referer': url,
},
}],
'uploader': uploader,
})
return info

4
youtube_dl/options.py
View File

@ -468,6 +468,10 @@ def parseOpts(overrideArguments=None):
'--abort-on-unavailable-fragment', '--abort-on-unavailable-fragment',
action='store_false', dest='skip_unavailable_fragments', action='store_false', dest='skip_unavailable_fragments',
help='Abort downloading when some fragment is not available') help='Abort downloading when some fragment is not available')
downloader.add_option(
'--keep-fragments',
action='store_true', dest='keep_fragments', default=False,
help='Keep downloaded fragments on disk after downloading is finished; fragments are erased by default')
downloader.add_option( downloader.add_option(
'--buffer-size', '--buffer-size',
dest='buffersize', metavar='SIZE', default='1024', dest='buffersize', metavar='SIZE', default='1024',

31
youtube_dl/postprocessor/ffmpeg.py
View File

@ -4,6 +4,7 @@ import io
import os import os
import subprocess import subprocess
import time import time
import re
from .common import AudioConversionError, PostProcessor from .common import AudioConversionError, PostProcessor
@ -22,6 +23,7 @@ from ..utils import (
subtitles_filename, subtitles_filename,
dfxp2srt, dfxp2srt,
ISO639Utils, ISO639Utils,
replace_extension,
) )
@ -429,17 +431,40 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
filename = info['filepath'] filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp') temp_filename = prepend_extension(filename, 'temp')
in_filenames = [filename]
options = []
if info['ext'] == 'm4a': if info['ext'] == 'm4a':
options = ['-vn', '-acodec', 'copy'] options.extend(['-vn', '-acodec', 'copy'])
else: else:
options = ['-c', 'copy'] options.extend(['-c', 'copy'])
for (name, value) in metadata.items(): for (name, value) in metadata.items():
options.extend(['-metadata', '%s=%s' % (name, value)]) options.extend(['-metadata', '%s=%s' % (name, value)])
chapters = info.get('chapters', [])
if chapters:
metadata_filename = encodeFilename(replace_extension(filename, 'meta'))
with io.open(metadata_filename, 'wt', encoding='utf-8') as f:
def ffmpeg_escape(text):
return re.sub(r'(=|;|#|\\|\n)', r'\\\1', text)
metadata_file_content = ';FFMETADATA1\n'
for chapter in chapters:
metadata_file_content += '[CHAPTER]\nTIMEBASE=1/1000\n'
metadata_file_content += 'START=%d\n' % (chapter['start_time'] * 1000)
metadata_file_content += 'END=%d\n' % (chapter['end_time'] * 1000)
chapter_title = chapter.get('title')
if chapter_title:
metadata_file_content += 'title=%s\n' % ffmpeg_escape(chapter_title)
f.write(metadata_file_content)
in_filenames.append(metadata_filename)
options.extend(['-map_metadata', '1'])
self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename) self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
self.run_ffmpeg(filename, temp_filename, options) self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
if chapters:
os.remove(metadata_filename)
os.remove(encodeFilename(filename)) os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return [], info return [], info

5
youtube_dl/socks.py
View File

@ -193,9 +193,10 @@ class sockssocket(socket.socket):
self._check_response_version(SOCKS5_VERSION, version) self._check_response_version(SOCKS5_VERSION, version)
if method == Socks5Auth.AUTH_NO_ACCEPTABLE: if method == Socks5Auth.AUTH_NO_ACCEPTABLE or (
method == Socks5Auth.AUTH_USER_PASS and (not self._proxy.username or not self._proxy.password)):
self.close() self.close()
raise Socks5Error(method) raise Socks5Error(Socks5Auth.AUTH_NO_ACCEPTABLE)
if method == Socks5Auth.AUTH_USER_PASS: if method == Socks5Auth.AUTH_USER_PASS:
username = self._proxy.username.encode('utf-8') username = self._proxy.username.encode('utf-8')

210
youtube_dl/utils.py
View File

@ -11,6 +11,7 @@ import contextlib
import ctypes import ctypes
import datetime import datetime
import email.utils import email.utils
import email.header
import errno import errno
import functools import functools
import gzip import gzip
@ -421,8 +422,8 @@ def clean_html(html):
# Newline vs <br /> # Newline vs <br />
html = html.replace('\n', ' ') html = html.replace('\n', ' ')
html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html) html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html) html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags # Strip html tags
html = re.sub('<.*?>', '', html) html = re.sub('<.*?>', '', html)
# Replace html entities # Replace html entities
@ -1194,6 +1195,11 @@ def unified_timestamp(date_str, day_first=True):
# Remove AM/PM + timezone # Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str) date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
# Remove unrecognized timezones from ISO 8601 alike timestamps
m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
if m:
date_str = date_str[:-len(m.group('tz'))]
for expression in date_formats(day_first): for expression in date_formats(day_first):
try: try:
dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta) dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
@ -2092,6 +2098,58 @@ def update_Request(req, url=None, data=None, headers={}, query={}):
return new_req return new_req
def try_multipart_encode(data, boundary):
content_type = 'multipart/form-data; boundary=%s' % boundary
out = b''
for k, v in data.items():
out += b'--' + boundary.encode('ascii') + b'\r\n'
if isinstance(k, compat_str):
k = k.encode('utf-8')
if isinstance(v, compat_str):
v = v.encode('utf-8')
# RFC 2047 requires non-ASCII field names to be encoded, while RFC 7578
# suggests sending UTF-8 directly. Firefox sends UTF-8, too
content = b'Content-Disposition: form-data; name="%s"\r\n\r\n' % k + v + b'\r\n'
if boundary.encode('ascii') in content:
raise ValueError('Boundary overlaps with data')
out += content
out += b'--' + boundary.encode('ascii') + b'--\r\n'
return out, content_type
def multipart_encode(data, boundary=None):
'''
Encode a dict to RFC 7578-compliant form-data
data:
A dict where keys and values can be either Unicode or bytes-like
objects.
boundary:
If specified a Unicode object, it's used as the boundary. Otherwise
a random boundary is generated.
Reference: https://tools.ietf.org/html/rfc7578
'''
has_specified_boundary = boundary is not None
while True:
if boundary is None:
boundary = '---------------' + str(random.randrange(0x0fffffff, 0xffffffff))
try:
out, content_type = try_multipart_encode(data, boundary)
break
except ValueError:
if has_specified_boundary:
raise
boundary = None
return out, content_type
def dict_get(d, key_or_keys, default=None, skip_false_values=True): def dict_get(d, key_or_keys, default=None, skip_false_values=True):
if isinstance(key_or_keys, (list, tuple)): if isinstance(key_or_keys, (list, tuple)):
for key in key_or_keys: for key in key_or_keys:
@ -2103,13 +2161,16 @@ def dict_get(d, key_or_keys, default=None, skip_false_values=True):
def try_get(src, getter, expected_type=None): def try_get(src, getter, expected_type=None):
try: if not isinstance(getter, (list, tuple)):
v = getter(src) getter = [getter]
except (AttributeError, KeyError, TypeError, IndexError): for get in getter:
pass try:
else: v = get(src)
if expected_type is None or isinstance(v, expected_type): except (AttributeError, KeyError, TypeError, IndexError):
return v pass
else:
if expected_type is None or isinstance(v, expected_type):
return v
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'): def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
@ -2270,10 +2331,8 @@ def mimetype2ext(mt):
return { return {
'3gpp': '3gp', '3gpp': '3gp',
'smptett+xml': 'tt', 'smptett+xml': 'tt',
'srt': 'srt',
'ttaf+xml': 'dfxp', 'ttaf+xml': 'dfxp',
'ttml+xml': 'ttml', 'ttml+xml': 'ttml',
'vtt': 'vtt',
'x-flv': 'flv', 'x-flv': 'flv',
'x-mp4-fragmented': 'mp4', 'x-mp4-fragmented': 'mp4',
'x-ms-wmv': 'wmv', 'x-ms-wmv': 'wmv',
@ -2281,11 +2340,11 @@ def mimetype2ext(mt):
'x-mpegurl': 'm3u8', 'x-mpegurl': 'm3u8',
'vnd.apple.mpegurl': 'm3u8', 'vnd.apple.mpegurl': 'm3u8',
'dash+xml': 'mpd', 'dash+xml': 'mpd',
'f4m': 'f4m',
'f4m+xml': 'f4m', 'f4m+xml': 'f4m',
'hds+xml': 'f4m', 'hds+xml': 'f4m',
'vnd.ms-sstr+xml': 'ism', 'vnd.ms-sstr+xml': 'ism',
'quicktime': 'mov', 'quicktime': 'mov',
'mp2t': 'ts',
}.get(res, res) }.get(res, res)
@ -2508,27 +2567,97 @@ def srt_subtitles_timecode(seconds):
def dfxp2srt(dfxp_data): def dfxp2srt(dfxp_data):
LEGACY_NAMESPACES = (
('http://www.w3.org/ns/ttml', [
'http://www.w3.org/2004/11/ttaf1',
'http://www.w3.org/2006/04/ttaf1',
'http://www.w3.org/2006/10/ttaf1',
]),
('http://www.w3.org/ns/ttml#styling', [
'http://www.w3.org/ns/ttml#style',
]),
)
SUPPORTED_STYLING = [
'color',
'fontFamily',
'fontSize',
'fontStyle',
'fontWeight',
'textDecoration'
]
_x = functools.partial(xpath_with_ns, ns_map={ _x = functools.partial(xpath_with_ns, ns_map={
'ttml': 'http://www.w3.org/ns/ttml', 'ttml': 'http://www.w3.org/ns/ttml',
'ttaf1': 'http://www.w3.org/2006/10/ttaf1', 'tts': 'http://www.w3.org/ns/ttml#styling',
'ttaf1_0604': 'http://www.w3.org/2006/04/ttaf1',
}) })
styles = {}
default_style = {}
class TTMLPElementParser(object): class TTMLPElementParser(object):
out = '' _out = ''
_unclosed_elements = []
_applied_styles = []
def start(self, tag, attrib): def start(self, tag, attrib):
if tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'): if tag in (_x('ttml:br'), 'br'):
self.out += '\n' self._out += '\n'
else:
unclosed_elements = []
style = {}
element_style_id = attrib.get('style')
if default_style:
style.update(default_style)
if element_style_id:
style.update(styles.get(element_style_id, {}))
for prop in SUPPORTED_STYLING:
prop_val = attrib.get(_x('tts:' + prop))
if prop_val:
style[prop] = prop_val
if style:
font = ''
for k, v in sorted(style.items()):
if self._applied_styles and self._applied_styles[-1].get(k) == v:
continue
if k == 'color':
font += ' color="%s"' % v
elif k == 'fontSize':
font += ' size="%s"' % v
elif k == 'fontFamily':
font += ' face="%s"' % v
elif k == 'fontWeight' and v == 'bold':
self._out += '<b>'
unclosed_elements.append('b')
elif k == 'fontStyle' and v == 'italic':
self._out += '<i>'
unclosed_elements.append('i')
elif k == 'textDecoration' and v == 'underline':
self._out += '<u>'
unclosed_elements.append('u')
if font:
self._out += '<font' + font + '>'
unclosed_elements.append('font')
applied_style = {}
if self._applied_styles:
applied_style.update(self._applied_styles[-1])
applied_style.update(style)
self._applied_styles.append(applied_style)
self._unclosed_elements.append(unclosed_elements)
def end(self, tag): def end(self, tag):
pass if tag not in (_x('ttml:br'), 'br'):
unclosed_elements = self._unclosed_elements.pop()
for element in reversed(unclosed_elements):
self._out += '</%s>' % element
if unclosed_elements and self._applied_styles:
self._applied_styles.pop()
def data(self, data): def data(self, data):
self.out += data self._out += data
def close(self): def close(self):
return self.out.strip() return self._out.strip()
def parse_node(node): def parse_node(node):
target = TTMLPElementParser() target = TTMLPElementParser()
@ -2536,13 +2665,45 @@ def dfxp2srt(dfxp_data):
parser.feed(xml.etree.ElementTree.tostring(node)) parser.feed(xml.etree.ElementTree.tostring(node))
return parser.close() return parser.close()
for k, v in LEGACY_NAMESPACES:
for ns in v:
dfxp_data = dfxp_data.replace(ns, k)
dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8')) dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
out = [] out = []
paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall(_x('.//ttaf1_0604:p')) or dfxp.findall('.//p') paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
if not paras: if not paras:
raise ValueError('Invalid dfxp/TTML subtitle') raise ValueError('Invalid dfxp/TTML subtitle')
repeat = False
while True:
for style in dfxp.findall(_x('.//ttml:style')):
style_id = style.get('id')
parent_style_id = style.get('style')
if parent_style_id:
if parent_style_id not in styles:
repeat = True
continue
styles[style_id] = styles[parent_style_id].copy()
for prop in SUPPORTED_STYLING:
prop_val = style.get(_x('tts:' + prop))
if prop_val:
styles.setdefault(style_id, {})[prop] = prop_val
if repeat:
repeat = False
else:
break
for p in ('body', 'div'):
ele = xpath_element(dfxp, [_x('.//ttml:' + p), './/' + p])
if ele is None:
continue
style = styles.get(ele.get('style'))
if not style:
continue
default_style.update(style)
for para, index in zip(paras, itertools.count(1)): for para, index in zip(paras, itertools.count(1)):
begin_time = parse_dfxp_time_expr(para.attrib.get('begin')) begin_time = parse_dfxp_time_expr(para.attrib.get('begin'))
end_time = parse_dfxp_time_expr(para.attrib.get('end')) end_time = parse_dfxp_time_expr(para.attrib.get('end'))
@ -3862,3 +4023,10 @@ class PhantomJSwrapper(object):
return (html, encodeArgument(out)) return (html, encodeArgument(out))
def random_birthday(year_field, month_field, day_field):
return {
year_field: str(random.randint(1950, 1995)),
month_field: str(random.randint(1, 12)),
day_field: str(random.randint(1, 31)),
}

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals from __future__ import unicode_literals
__version__ = '2017.04.15' __version__ = '2017.05.01'