mirror of
https://codeberg.org/polarisfm/youtube-dl
synced 2025-01-06 05:07:54 +01:00
Merge remote-tracking branch 'upstream/master' into fix-zing-mp3
This commit is contained in:
Thinh Nguyen
commit
0fae6aeb2a
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.11.23*. 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 Issues with outdated version will be rejected.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 **2018.11.23**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.12.17*. 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 Issues with outdated version will be rejected.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 **2018.12.17**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
|
||||
[debug] User config: []
|
||||
[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] youtube-dl version 2018.11.23
|
||||
[debug] youtube-dl version 2018.12.17
|
||||
[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] Proxy map: {}
|
||||
|
||||
@ -152,7 +152,7 @@ After you have ensured this site is distributing its content legally, you can fo
|
||||
```
|
||||
5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
|
||||
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
|
||||
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
|
||||
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
|
||||
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
|
||||
9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
|
||||
|
||||
@ -173,7 +173,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou
|
||||
|
||||
### Mandatory and optional metafields
|
||||
|
||||
For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
|
||||
For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
|
||||
|
||||
- `id` (media identifier)
|
||||
- `title` (media title)
|
||||
@ -181,7 +181,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and
|
||||
|
||||
In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
|
||||
|
||||
[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
|
||||
[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
|
||||
|
||||
#### Example
|
||||
|
||||
|
||||
59
ChangeLog
59
ChangeLog
@ -1,3 +1,62 @@
|
||||
version 2018.12.17
|
||||
|
||||
Extractors
|
||||
* [ard:beta] Improve geo restricted videos extraction
|
||||
* [ard:beta] Fix subtitles extraction
|
||||
* [ard:beta] Improve extraction robustness
|
||||
* [ard:beta] Relax URL regular expression (#18441)
|
||||
* [acast] Add support for embed.acast.com and play.acast.com (#18483)
|
||||
* [iprima] Relax URL regular expression (#18515, #18540)
|
||||
* [vrv] Fix initial state extraction (#18553)
|
||||
* [youtube] Fix mark watched (#18546)
|
||||
+ [safari] Add support for learning.oreilly.com (#18510)
|
||||
* [youtube] Fix multifeed extraction (#18531)
|
||||
* [lecturio] Improve subtitles extraction (#18488)
|
||||
* [uol] Fix format URL extraction (#18480)
|
||||
+ [ard:mediathek] Add support for classic.ardmediathek.de (#18473)
|
||||
|
||||
|
||||
version 2018.12.09
|
||||
|
||||
Core
|
||||
* [YoutubeDL] Keep session cookies in cookie file between runs
|
||||
* [YoutubeDL] Recognize session cookies with expired set to 0 (#12929)
|
||||
|
||||
Extractors
|
||||
+ [teachable] Add support for teachable platform sites (#5451, #18150, #18272)
|
||||
+ [aenetworks] Add support for historyvault.com (#18460)
|
||||
* [imgur] Improve gallery and album detection and extraction (#9133, #16577,
|
||||
#17223, #18404)
|
||||
* [iprima] Relax URL regular expression (#18453)
|
||||
* [hotstar] Fix video data extraction (#18386)
|
||||
* [ard:mediathek] Fix title and description extraction (#18349, #18371)
|
||||
* [xvideos] Switch to HTTPS (#18422, #18427)
|
||||
+ [lecturio] Add support for lecturio.com (#18405)
|
||||
+ [nrktv:series] Add support for extra materials
|
||||
* [nrktv:season,series] Fix extraction (#17159, #17258)
|
||||
* [nrktv] Relax URL regular expression (#18304, #18387)
|
||||
* [yourporn] Fix extraction (#18424, #18425)
|
||||
* [tbs] Fix info extraction (#18403)
|
||||
+ [gamespot] Add support for review URLs
|
||||
|
||||
|
||||
version 2018.12.03
|
||||
|
||||
Core
|
||||
* [utils] Fix random_birthday to generate existing dates only (#18284)
|
||||
|
||||
Extractors
|
||||
+ [tiktok] Add support for tiktok.com (#18108, #18135)
|
||||
* [pornhub] Use actual URL host for requests (#18359)
|
||||
* [lynda] Fix authentication (#18158, #18217)
|
||||
* [gfycat] Update API endpoint (#18333, #18343)
|
||||
+ [hotstar] Add support for alternative app state layout (#18320)
|
||||
* [azmedien] Fix extraction (#18334, #18336)
|
||||
+ [vimeo] Add support for VHX (Vimeo OTT) (#14835)
|
||||
* [joj] Fix extraction (#18280, #18281)
|
||||
+ [wistia] Add support for fast.wistia.com (#18287)
|
||||
|
||||
|
||||
version 2018.11.23
|
||||
|
||||
Core
|
||||
|
||||
16
README.md
16
README.md
@ -1024,16 +1024,20 @@ After you have ensured this site is distributing its content legally, you can fo
|
||||
```
|
||||
5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
|
||||
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
|
||||
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want.
|
||||
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
|
||||
9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
|
||||
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
|
||||
8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
|
||||
|
||||
$ flake8 youtube_dl/extractor/yourextractor.py
|
||||
|
||||
9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+.
|
||||
10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
|
||||
|
||||
$ git add youtube_dl/extractor/extractors.py
|
||||
$ git add youtube_dl/extractor/yourextractor.py
|
||||
$ git commit -m '[yourextractor] Add new extractor'
|
||||
$ git push origin yourextractor
|
||||
|
||||
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
|
||||
11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
|
||||
|
||||
In any case, thank you very much for your contributions!
|
||||
|
||||
@ -1045,7 +1049,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou
|
||||
|
||||
### Mandatory and optional metafields
|
||||
|
||||
For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
|
||||
For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl:
|
||||
|
||||
- `id` (media identifier)
|
||||
- `title` (media title)
|
||||
@ -1053,7 +1057,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and
|
||||
|
||||
In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken.
|
||||
|
||||
[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
|
||||
[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
|
||||
|
||||
#### Example
|
||||
|
||||
|
||||
@ -33,7 +33,7 @@
|
||||
- **AdobeTVShow**
|
||||
- **AdobeTVVideo**
|
||||
- **AdultSwim**
|
||||
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
|
||||
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
|
||||
- **afreecatv**: afreecatv.com
|
||||
- **AirMozilla**
|
||||
- **AliExpressLive**
|
||||
@ -376,7 +376,8 @@
|
||||
- **imdb**: Internet Movie Database trailers
|
||||
- **imdb:list**: Internet Movie Database lists
|
||||
- **Imgur**
|
||||
- **ImgurAlbum**
|
||||
- **imgur:album**
|
||||
- **imgur:gallery**
|
||||
- **Ina**
|
||||
- **Inc**
|
||||
- **IndavideoEmbed**
|
||||
@ -435,6 +436,8 @@
|
||||
- **Le**: 乐视网
|
||||
- **Learnr**
|
||||
- **Lecture2Go**
|
||||
- **Lecturio**
|
||||
- **LecturioCourse**
|
||||
- **LEGO**
|
||||
- **Lemonde**
|
||||
- **Lenta**
|
||||
@ -853,6 +856,8 @@
|
||||
- **TastyTrade**
|
||||
- **TBS**
|
||||
- **TDSLifeway**
|
||||
- **Teachable**
|
||||
- **TeachableCourse**
|
||||
- **teachertube**: teachertube.com videos
|
||||
- **teachertube:user:collection**: teachertube.com user and collection videos
|
||||
- **TeachingChannel**
|
||||
@ -885,6 +890,8 @@
|
||||
- **ThisAmericanLife**
|
||||
- **ThisAV**
|
||||
- **ThisOldHouse**
|
||||
- **TikTok**
|
||||
- **TikTokUser**
|
||||
- **tinypic**: tinypic.com videos
|
||||
- **TMZ**
|
||||
- **TMZArticle**
|
||||
@ -959,8 +966,6 @@
|
||||
- **uol.com.br**
|
||||
- **uplynk**
|
||||
- **uplynk:preplay**
|
||||
- **Upskill**
|
||||
- **UpskillCourse**
|
||||
- **Urort**: NRK P3 Urørt
|
||||
- **URPlay**
|
||||
- **USANetwork**
|
||||
@ -979,6 +984,7 @@
|
||||
- **VevoPlaylist**
|
||||
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
|
||||
- **vh1.com**
|
||||
- **vhx:embed**
|
||||
- **Viafree**
|
||||
- **vice**
|
||||
- **vice:article**
|
||||
|
||||
34
test/test_YoutubeDLCookieJar.py
Normal file
34
test/test_YoutubeDLCookieJar.py
Normal file
@ -0,0 +1,34 @@
|
||||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from youtube_dl.utils import YoutubeDLCookieJar
|
||||
|
||||
|
||||
class TestYoutubeDLCookieJar(unittest.TestCase):
|
||||
def test_keep_session_cookies(self):
|
||||
cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
|
||||
cookiejar.load(ignore_discard=True, ignore_expires=True)
|
||||
tf = tempfile.NamedTemporaryFile(delete=False)
|
||||
try:
|
||||
cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True)
|
||||
temp = tf.read().decode('utf-8')
|
||||
self.assertTrue(re.search(
|
||||
r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp))
|
||||
self.assertTrue(re.search(
|
||||
r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp))
|
||||
finally:
|
||||
tf.close()
|
||||
os.remove(tf.name)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
6
test/testdata/cookies/session_cookies.txt
vendored
Normal file
6
test/testdata/cookies/session_cookies.txt
vendored
Normal file
@ -0,0 +1,6 @@
|
||||
# Netscape HTTP Cookie File
|
||||
# http://curl.haxx.se/rfc/cookie_spec.html
|
||||
# This is a generated file! Do not edit.
|
||||
|
||||
www.foobar.foobar FALSE / TRUE YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue
|
||||
www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value
|
||||
@ -88,6 +88,7 @@ from .utils import (
|
||||
version_tuple,
|
||||
write_json_file,
|
||||
write_string,
|
||||
YoutubeDLCookieJar,
|
||||
YoutubeDLCookieProcessor,
|
||||
YoutubeDLHandler,
|
||||
)
|
||||
@ -558,7 +559,7 @@ class YoutubeDL(object):
|
||||
self.restore_console_title()
|
||||
|
||||
if self.params.get('cookiefile') is not None:
|
||||
self.cookiejar.save()
|
||||
self.cookiejar.save(ignore_discard=True, ignore_expires=True)
|
||||
|
||||
def trouble(self, message=None, tb=None):
|
||||
"""Determine action to take when a download problem appears.
|
||||
@ -2297,10 +2298,9 @@ class YoutubeDL(object):
|
||||
self.cookiejar = compat_cookiejar.CookieJar()
|
||||
else:
|
||||
opts_cookiefile = expand_path(opts_cookiefile)
|
||||
self.cookiejar = compat_cookiejar.MozillaCookieJar(
|
||||
opts_cookiefile)
|
||||
self.cookiejar = YoutubeDLCookieJar(opts_cookiefile)
|
||||
if os.access(opts_cookiefile, os.R_OK):
|
||||
self.cookiejar.load()
|
||||
self.cookiejar.load(ignore_discard=True, ignore_expires=True)
|
||||
|
||||
cookie_processor = YoutubeDLCookieProcessor(self.cookiejar)
|
||||
if opts_proxy is not None:
|
||||
|
||||
@ -17,25 +17,15 @@ from ..utils import (
|
||||
|
||||
class ACastIE(InfoExtractor):
|
||||
IE_NAME = 'acast'
|
||||
_VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:(?:embed|www)\.)?acast\.com/|
|
||||
play\.acast\.com/s/
|
||||
)
|
||||
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
# test with one bling
|
||||
'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
|
||||
'md5': 'ada3de5a1e3a2a381327d749854788bb',
|
||||
'info_dict': {
|
||||
'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
|
||||
'ext': 'mp3',
|
||||
'title': '"Where Are You?": Taipei 101, Taiwan',
|
||||
'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
|
||||
'timestamp': 1196172000,
|
||||
'upload_date': '20071127',
|
||||
'duration': 211,
|
||||
'creator': 'Concierge',
|
||||
'series': 'Condé Nast Traveler Podcast',
|
||||
'episode': '"Where Are You?": Taipei 101, Taiwan',
|
||||
}
|
||||
}, {
|
||||
# test with multiple blings
|
||||
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
|
||||
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
|
||||
'info_dict': {
|
||||
@ -50,6 +40,12 @@ class ACastIE(InfoExtractor):
|
||||
'series': 'Spår',
|
||||
'episode': '2. Raggarmordet - Röster ur det förflutna',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE):
|
||||
|
||||
class AENetworksIE(AENetworksBaseIE):
|
||||
IE_NAME = 'aenetworks'
|
||||
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
|
||||
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?
|
||||
(?P<domain>
|
||||
(?:history|aetv|mylifetime|lifetimemovieclub)\.com|
|
||||
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
|
||||
fyi\.tv
|
||||
)/
|
||||
(?:
|
||||
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
|
||||
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
|
||||
specials/(?P<special_display_id>[^/]+)/full-special
|
||||
specials/(?P<special_display_id>[^/]+)/full-special|
|
||||
collections/[^/]+/(?P<collection_display_id>[^/]+)
|
||||
)
|
||||
'''
|
||||
_TESTS = [{
|
||||
@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
|
||||
'only_matching': True
|
||||
}]
|
||||
_DOMAIN_TO_REQUESTOR_ID = {
|
||||
'history.com': 'HISTORY',
|
||||
@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE):
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
|
||||
display_id = show_path or movie_display_id or special_display_id
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
|
||||
display_id = show_path or movie_display_id or special_display_id or collection_display_id
|
||||
webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
|
||||
if show_path:
|
||||
url_parts = show_path.split('/')
|
||||
url_parts_len = len(url_parts)
|
||||
|
||||
@ -8,20 +8,23 @@ from .generic import GenericIE
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
qualities,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
qualities,
|
||||
str_or_none,
|
||||
try_get,
|
||||
unified_strdate,
|
||||
xpath_text,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
url_or_none,
|
||||
xpath_text,
|
||||
)
|
||||
from ..compat import compat_etree_fromstring
|
||||
|
||||
|
||||
class ARDMediathekIE(InfoExtractor):
|
||||
IE_NAME = 'ARD:mediathek'
|
||||
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
|
||||
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
|
||||
|
||||
_TESTS = [{
|
||||
# available till 26.07.2022
|
||||
@ -51,8 +54,15 @@ class ARDMediathekIE(InfoExtractor):
|
||||
# audio
|
||||
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
|
||||
|
||||
def _extract_media_info(self, media_info_url, webpage, video_id):
|
||||
media_info = self._download_json(
|
||||
media_info_url, video_id, 'Downloading media JSON')
|
||||
@ -173,13 +183,18 @@ class ARDMediathekIE(InfoExtractor):
|
||||
title = self._html_search_regex(
|
||||
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
|
||||
r'<meta name="dcterms\.title" content="(.*?)"/>',
|
||||
r'<h4 class="headline">(.*?)</h4>'],
|
||||
r'<h4 class="headline">(.*?)</h4>',
|
||||
r'<title[^>]*>(.*?)</title>'],
|
||||
webpage, 'title')
|
||||
description = self._html_search_meta(
|
||||
'dcterms.abstract', webpage, 'description', default=None)
|
||||
if description is None:
|
||||
description = self._html_search_meta(
|
||||
'description', webpage, 'meta description')
|
||||
'description', webpage, 'meta description', default=None)
|
||||
if description is None:
|
||||
description = self._html_search_regex(
|
||||
r'<p\s+class="teasertext">(.+?)</p>',
|
||||
webpage, 'teaser text', default=None)
|
||||
|
||||
# Thumbnail is sometimes not present.
|
||||
# It is in the mobile version, but that seems to use a different URL
|
||||
@ -288,7 +303,7 @@ class ARDIE(InfoExtractor):
|
||||
|
||||
|
||||
class ARDBetaMediathekIE(InfoExtractor):
|
||||
_VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)'
|
||||
_VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
|
||||
_TESTS = [{
|
||||
'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
|
||||
'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
|
||||
@ -302,12 +317,18 @@ class ARDBetaMediathekIE(InfoExtractor):
|
||||
'upload_date': '20180826',
|
||||
'ext': 'mp4',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
display_id = mobj.group('display_id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')
|
||||
@ -318,43 +339,62 @@ class ARDBetaMediathekIE(InfoExtractor):
|
||||
'display_id': display_id,
|
||||
}
|
||||
formats = []
|
||||
subtitles = {}
|
||||
geoblocked = False
|
||||
for widget in data.values():
|
||||
if widget.get('_geoblocked'):
|
||||
raise ExtractorError('This video is not available due to geoblocking', expected=True)
|
||||
|
||||
if widget.get('_geoblocked') is True:
|
||||
geoblocked = True
|
||||
if '_duration' in widget:
|
||||
res['duration'] = widget['_duration']
|
||||
res['duration'] = int_or_none(widget['_duration'])
|
||||
if 'clipTitle' in widget:
|
||||
res['title'] = widget['clipTitle']
|
||||
if '_previewImage' in widget:
|
||||
res['thumbnail'] = widget['_previewImage']
|
||||
if 'broadcastedOn' in widget:
|
||||
res['upload_date'] = unified_strdate(widget['broadcastedOn'])
|
||||
res['timestamp'] = unified_timestamp(widget['broadcastedOn'])
|
||||
if 'synopsis' in widget:
|
||||
res['description'] = widget['synopsis']
|
||||
if '_subtitleUrl' in widget:
|
||||
res['subtitles'] = {'de': [{
|
||||
subtitle_url = url_or_none(widget.get('_subtitleUrl'))
|
||||
if subtitle_url:
|
||||
subtitles.setdefault('de', []).append({
|
||||
'ext': 'ttml',
|
||||
'url': widget['_subtitleUrl'],
|
||||
}]}
|
||||
'url': subtitle_url,
|
||||
})
|
||||
if '_quality' in widget:
|
||||
format_url = widget['_stream']['json'][0]
|
||||
|
||||
if format_url.endswith('.f4m'):
|
||||
format_url = url_or_none(try_get(
|
||||
widget, lambda x: x['_stream']['json'][0]))
|
||||
if not format_url:
|
||||
continue
|
||||
ext = determine_ext(format_url)
|
||||
if ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
format_url + '?hdcore=3.11.0',
|
||||
video_id, f4m_id='hds', fatal=False))
|
||||
elif format_url.endswith('m3u8'):
|
||||
elif ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
||||
format_url, video_id, 'mp4', m3u8_id='hls',
|
||||
fatal=False))
|
||||
else:
|
||||
# HTTP formats are not available when geoblocked is True,
|
||||
# other formats are fine though
|
||||
if geoblocked:
|
||||
continue
|
||||
quality = str_or_none(widget.get('_quality'))
|
||||
formats.append({
|
||||
'format_id': 'http-' + widget['_quality'],
|
||||
'format_id': ('http-' + quality) if quality else 'http',
|
||||
'url': format_url,
|
||||
'preference': 10, # Plain HTTP, that's nice
|
||||
})
|
||||
|
||||
if not formats and geoblocked:
|
||||
self.raise_geo_restricted(
|
||||
msg='This video is not available due to geoblocking',
|
||||
countries=['DE'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
res['formats'] = formats
|
||||
res.update({
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return res
|
||||
|
||||
@ -36,7 +36,6 @@ class AZMedienIE(InfoExtractor):
|
||||
'id': '1_anruz3wy',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
|
||||
'description': 'md5:dd9f96751ec9c35e409a698a328402f3',
|
||||
'uploader_id': 'TVOnline',
|
||||
'upload_date': '20180930',
|
||||
'timestamp': 1538328802,
|
||||
@ -53,15 +52,12 @@ class AZMedienIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
video_id = mobj.group('id')
|
||||
entry_id = mobj.group('kaltura_id')
|
||||
|
||||
if not entry_id:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
api_path = self._search_regex(
|
||||
r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']',
|
||||
webpage, 'api path')
|
||||
api_url = 'https://www.%s%s' % (mobj.group('host'), api_path)
|
||||
api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0])
|
||||
payload = {
|
||||
'query': '''query VideoContext($articleId: ID!) {
|
||||
article: node(id: $articleId) {
|
||||
|
||||
@ -48,6 +48,21 @@ class CrackleIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_MEDIA_FILE_SLOTS = {
|
||||
'360p.mp4': {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
},
|
||||
'480p.mp4': {
|
||||
'width': 768,
|
||||
'height': 432,
|
||||
},
|
||||
'480p_1mbps.mp4': {
|
||||
'width': 852,
|
||||
'height': 480,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
@ -95,6 +110,20 @@ class CrackleIE(InfoExtractor):
|
||||
elif ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
format_url, video_id, mpd_id='dash', fatal=False))
|
||||
elif format_url.endswith('.ism/Manifest'):
|
||||
formats.extend(self._extract_ism_formats(
|
||||
format_url, video_id, ism_id='mss', fatal=False))
|
||||
else:
|
||||
mfs_path = e.get('Type')
|
||||
mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path)
|
||||
if not mfs_info:
|
||||
continue
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': 'http-' + mfs_path.split('.')[0],
|
||||
'width': mfs_info['width'],
|
||||
'height': mfs_info['height'],
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
description = media.get('Description')
|
||||
|
||||
@ -17,16 +17,29 @@ from ..compat import compat_HTTPError
|
||||
|
||||
|
||||
class DiscoveryIE(DiscoveryGoBaseIE):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>
|
||||
discovery|
|
||||
investigationdiscovery|
|
||||
discoverylife|
|
||||
animalplanet|
|
||||
ahctv|
|
||||
destinationamerica|
|
||||
sciencechannel|
|
||||
tlc|
|
||||
velocity
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?P<site>
|
||||
(?:www\.)?
|
||||
(?:
|
||||
discovery|
|
||||
investigationdiscovery|
|
||||
discoverylife|
|
||||
animalplanet|
|
||||
ahctv|
|
||||
destinationamerica|
|
||||
sciencechannel|
|
||||
tlc|
|
||||
velocity
|
||||
)|
|
||||
watch\.
|
||||
(?:
|
||||
hgtv|
|
||||
foodnetwork|
|
||||
travelchannel|
|
||||
diynetwork|
|
||||
cookingchanneltv|
|
||||
motortrend
|
||||
)
|
||||
)\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley',
|
||||
@ -71,7 +84,7 @@ class DiscoveryIE(DiscoveryGoBaseIE):
|
||||
|
||||
if not access_token:
|
||||
access_token = self._download_json(
|
||||
'https://www.%s.com/anonymous' % site, display_id, query={
|
||||
'https://%s.com/anonymous' % site, display_id, query={
|
||||
'authRel': 'authorization',
|
||||
'client_id': try_get(
|
||||
react_data, lambda x: x['application']['apiClientId'],
|
||||
|
||||
@ -483,6 +483,7 @@ from .imdb import (
|
||||
from .imgur import (
|
||||
ImgurIE,
|
||||
ImgurAlbumIE,
|
||||
ImgurGalleryIE,
|
||||
)
|
||||
from .ina import InaIE
|
||||
from .inc import IncIE
|
||||
@ -553,6 +554,11 @@ from .lcp import (
|
||||
)
|
||||
from .learnr import LearnrIE
|
||||
from .lecture2go import Lecture2GoIE
|
||||
from .lecturio import (
|
||||
LecturioIE,
|
||||
LecturioCourseIE,
|
||||
LecturioDeCourseIE,
|
||||
)
|
||||
from .leeco import (
|
||||
LeIE,
|
||||
LePlaylistIE,
|
||||
@ -1086,6 +1092,10 @@ from .tass import TassIE
|
||||
from .tastytrade import TastyTradeIE
|
||||
from .tbs import TBSIE
|
||||
from .tdslifeway import TDSLifewayIE
|
||||
from .teachable import (
|
||||
TeachableIE,
|
||||
TeachableCourseIE,
|
||||
)
|
||||
from .teachertube import (
|
||||
TeacherTubeIE,
|
||||
TeacherTubeUserIE,
|
||||
@ -1124,6 +1134,10 @@ from .thisamericanlife import ThisAmericanLifeIE
|
||||
from .thisav import ThisAVIE
|
||||
from .thisoldhouse import ThisOldHouseIE
|
||||
from .threeqsdn import ThreeQSDNIE
|
||||
from .tiktok import (
|
||||
TikTokIE,
|
||||
TikTokUserIE,
|
||||
)
|
||||
from .tinypic import TinyPicIE
|
||||
from .tmz import (
|
||||
TMZIE,
|
||||
@ -1231,10 +1245,6 @@ from .uplynk import (
|
||||
UplynkIE,
|
||||
UplynkPreplayIE,
|
||||
)
|
||||
from .upskill import (
|
||||
UpskillIE,
|
||||
UpskillCourseIE,
|
||||
)
|
||||
from .urort import UrortIE
|
||||
from .urplay import URPlayIE
|
||||
from .usanetwork import USANetworkIE
|
||||
@ -1303,6 +1313,7 @@ from .vimeo import (
|
||||
VimeoReviewIE,
|
||||
VimeoUserIE,
|
||||
VimeoWatchLaterIE,
|
||||
VHXEmbedIE,
|
||||
)
|
||||
from .vimple import VimpleIE
|
||||
from .vine import (
|
||||
|
||||
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class GameSpotIE(OnceIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
|
||||
'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
|
||||
@ -41,6 +41,9 @@ class GameSpotIE(OnceIE):
|
||||
}, {
|
||||
'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -109,6 +109,7 @@ from .vice import ViceIE
|
||||
from .xfileshare import XFileShareIE
|
||||
from .cloudflarestream import CloudflareStreamIE
|
||||
from .peertube import PeerTubeIE
|
||||
from .teachable import TeachableIE
|
||||
from .indavideo import IndavideoEmbedIE
|
||||
from .apa import APAIE
|
||||
from .foxnews import FoxNewsIE
|
||||
@ -3112,6 +3113,10 @@ class GenericIE(InfoExtractor):
|
||||
return self.playlist_from_matches(
|
||||
peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
|
||||
|
||||
teachable_url = TeachableIE._extract_url(webpage, url)
|
||||
if teachable_url:
|
||||
return self.url_result(teachable_url)
|
||||
|
||||
indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
|
||||
if indavideo_urls:
|
||||
return self.playlist_from_matches(
|
||||
|
||||
@ -53,7 +53,7 @@ class GfycatIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
gfy = self._download_json(
|
||||
'http://gfycat.com/cajax/get/%s' % video_id,
|
||||
'https://api.gfycat.com/v1/gfycats/%s' % video_id,
|
||||
video_id, 'Downloading video info')
|
||||
if 'error' in gfy:
|
||||
raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
|
||||
|
||||
@ -43,6 +43,7 @@ class HotStarIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar'
|
||||
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
|
||||
_TESTS = [{
|
||||
# contentData
|
||||
'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
|
||||
'info_dict': {
|
||||
'id': '1000076273',
|
||||
@ -57,6 +58,10 @@ class HotStarIE(HotStarBaseIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
# contentDetail
|
||||
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
|
||||
'only_matching': True,
|
||||
@ -74,10 +79,15 @@ class HotStarIE(HotStarBaseIE):
|
||||
r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
|
||||
webpage, 'app state'), video_id)
|
||||
video_data = {}
|
||||
getters = list(
|
||||
lambda x, k=k: x['initialState']['content%s' % k]['content']
|
||||
for k in ('Data', 'Detail')
|
||||
)
|
||||
for v in app_state.values():
|
||||
content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict)
|
||||
content = try_get(v, getters, dict)
|
||||
if content and content.get('contentId') == video_id:
|
||||
video_data = content
|
||||
break
|
||||
|
||||
title = video_data['title']
|
||||
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class ImgurIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$'
|
||||
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P<id>[a-zA-Z0-9]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://i.imgur.com/A61SaA1.gifv',
|
||||
@ -20,28 +20,9 @@ class ImgurIE(InfoExtractor):
|
||||
'id': 'A61SaA1',
|
||||
'ext': 'mp4',
|
||||
'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
|
||||
'description': 'Imgur: The magic of the Internet',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://imgur.com/A61SaA1',
|
||||
'info_dict': {
|
||||
'id': 'A61SaA1',
|
||||
'ext': 'mp4',
|
||||
'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
|
||||
'description': 'Imgur: The magic of the Internet',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://imgur.com/gallery/YcAQlkx',
|
||||
'info_dict': {
|
||||
'id': 'YcAQlkx',
|
||||
'ext': 'mp4',
|
||||
'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://imgur.com/topic/Funny/N8rOudd',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://imgur.com/r/aww/VQcQPhM',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://i.imgur.com/crGpqCV.mp4',
|
||||
@ -50,8 +31,8 @@ class ImgurIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
gifv_url = 'https://i.imgur.com/{id}.gifv'.format(id=video_id)
|
||||
webpage = self._download_webpage(gifv_url, video_id)
|
||||
webpage = self._download_webpage(
|
||||
'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id)
|
||||
|
||||
width = int_or_none(self._og_search_property(
|
||||
'video:width', webpage, default=None))
|
||||
@ -72,7 +53,6 @@ class ImgurIE(InfoExtractor):
|
||||
'format_id': m.group('type').partition('/')[2],
|
||||
'url': self._proto_relative_url(m.group('src')),
|
||||
'ext': mimetype2ext(m.group('type')),
|
||||
'acodec': 'none',
|
||||
'width': width,
|
||||
'height': height,
|
||||
'http_headers': {
|
||||
@ -107,44 +87,64 @@ class ImgurIE(InfoExtractor):
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'description': self._og_search_description(webpage, default=None),
|
||||
'title': self._og_search_title(webpage),
|
||||
}
|
||||
|
||||
|
||||
class ImgurAlbumIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{5})(?:[/?#&]+)?$'
|
||||
class ImgurGalleryIE(InfoExtractor):
|
||||
IE_NAME = 'imgur:gallery'
|
||||
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P<id>[a-zA-Z0-9]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://imgur.com/gallery/Q95ko',
|
||||
'info_dict': {
|
||||
'id': 'Q95ko',
|
||||
'title': 'Adding faces make every GIF better',
|
||||
},
|
||||
'playlist_count': 25,
|
||||
}, {
|
||||
'url': 'http://imgur.com/a/j6Orj',
|
||||
'url': 'http://imgur.com/topic/Aww/ll5Vk',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://imgur.com/topic/Aww/ll5Vk',
|
||||
'url': 'https://imgur.com/gallery/YcAQlkx',
|
||||
'info_dict': {
|
||||
'id': 'YcAQlkx',
|
||||
'ext': 'mp4',
|
||||
'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://imgur.com/topic/Funny/N8rOudd',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://imgur.com/r/aww/VQcQPhM',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
album_id = self._match_id(url)
|
||||
gallery_id = self._match_id(url)
|
||||
|
||||
album_images = self._download_json(
|
||||
'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
|
||||
album_id, fatal=False)
|
||||
data = self._download_json(
|
||||
'https://imgur.com/gallery/%s.json' % gallery_id,
|
||||
gallery_id)['data']['image']
|
||||
|
||||
if album_images:
|
||||
data = album_images.get('data')
|
||||
if data and isinstance(data, dict):
|
||||
images = data.get('images')
|
||||
if images and isinstance(images, list):
|
||||
entries = [
|
||||
self.url_result('http://imgur.com/%s' % image['hash'])
|
||||
for image in images if image.get('hash')]
|
||||
return self.playlist_result(entries, album_id)
|
||||
if data.get('is_album'):
|
||||
entries = [
|
||||
self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash'])
|
||||
for image in data['album_images']['images'] if image.get('hash')]
|
||||
return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description'))
|
||||
|
||||
# Fallback to single video
|
||||
return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key())
|
||||
return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id)
|
||||
|
||||
|
||||
class ImgurAlbumIE(ImgurGalleryIE):
|
||||
IE_NAME = 'imgur:album'
|
||||
_VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://imgur.com/a/j6Orj',
|
||||
'info_dict': {
|
||||
'id': 'j6Orj',
|
||||
'title': 'A Literary Analysis of "Star Wars: The Force Awakens"',
|
||||
},
|
||||
'playlist_count': 12,
|
||||
}]
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class IPrimaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
|
||||
_VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_GEO_BYPASS = False
|
||||
|
||||
_TESTS = [{
|
||||
@ -41,6 +41,24 @@ class IPrimaIE(InfoExtractor):
|
||||
# iframe prima.iprima.cz
|
||||
'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.iprima.cz/filmy/desne-rande',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://cool.iprima.cz/derava-silnice-nevadi',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -61,7 +61,7 @@ class JojIE(InfoExtractor):
|
||||
|
||||
bitrates = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates',
|
||||
r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',
|
||||
default='{}'),
|
||||
video_id, transform_source=js_to_json, fatal=False)
|
||||
|
||||
|
||||
229
youtube_dl/extractor/lecturio.py
Normal file
229
youtube_dl/extractor/lecturio.py
Normal file
@ -0,0 +1,229 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class LecturioBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'https://app.lecturio.com/en/login'
|
||||
_NETRC_MACHINE = 'lecturio'
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
|
||||
# Sets some cookies
|
||||
_, urlh = self._download_webpage_handle(
|
||||
self._LOGIN_URL, None, 'Downloading login popup')
|
||||
|
||||
def is_logged(url_handle):
|
||||
return self._LOGIN_URL not in compat_str(url_handle.geturl())
|
||||
|
||||
# Already logged in
|
||||
if is_logged(urlh):
|
||||
return
|
||||
|
||||
login_form = {
|
||||
'signin[email]': username,
|
||||
'signin[password]': password,
|
||||
'signin[remember]': 'on',
|
||||
}
|
||||
|
||||
response, urlh = self._download_webpage_handle(
|
||||
self._LOGIN_URL, None, 'Logging in',
|
||||
data=urlencode_postdata(login_form))
|
||||
|
||||
# Logged in successfully
|
||||
if is_logged(urlh):
|
||||
return
|
||||
|
||||
errors = self._html_search_regex(
|
||||
r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response,
|
||||
'errors', default=None)
|
||||
if errors:
|
||||
raise ExtractorError('Unable to login: %s' % errors, expected=True)
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
|
||||
class LecturioIE(LecturioBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https://
|
||||
(?:
|
||||
app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
|
||||
(?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
|
||||
)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
|
||||
'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
|
||||
'info_dict': {
|
||||
'id': '39634',
|
||||
'ext': 'mp4',
|
||||
'title': 'Important Concepts and Terms – Introduction to Microbiology',
|
||||
},
|
||||
'skip': 'Requires lecturio account credentials',
|
||||
}, {
|
||||
'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_CC_LANGS = {
|
||||
'German': 'de',
|
||||
'English': 'en',
|
||||
'Spanish': 'es',
|
||||
'French': 'fr',
|
||||
'Polish': 'pl',
|
||||
'Russian': 'ru',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('id') or mobj.group('id_de')
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
|
||||
display_id)
|
||||
|
||||
lecture_id = self._search_regex(
|
||||
r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
|
||||
|
||||
api_url = self._search_regex(
|
||||
r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
|
||||
'api url', group='url')
|
||||
|
||||
video = self._download_json(api_url, display_id)
|
||||
|
||||
title = video['title'].strip()
|
||||
|
||||
formats = []
|
||||
for format_ in video['content']['media']:
|
||||
if not isinstance(format_, dict):
|
||||
continue
|
||||
file_ = format_.get('file')
|
||||
if not file_:
|
||||
continue
|
||||
ext = determine_ext(file_)
|
||||
if ext == 'smil':
|
||||
# smil contains only broken RTMP formats anyway
|
||||
continue
|
||||
file_url = url_or_none(file_)
|
||||
if not file_url:
|
||||
continue
|
||||
label = str_or_none(format_.get('label'))
|
||||
filesize = int_or_none(format_.get('fileSize'))
|
||||
formats.append({
|
||||
'url': file_url,
|
||||
'format_id': label,
|
||||
'filesize': float_or_none(filesize, invscale=1000)
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
automatic_captions = {}
|
||||
cc = self._parse_json(
|
||||
self._search_regex(
|
||||
r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
|
||||
default='{}'), display_id, fatal=False)
|
||||
for cc_label, cc_url in cc.items():
|
||||
cc_url = url_or_none(cc_url)
|
||||
if not cc_url:
|
||||
continue
|
||||
lang = self._search_regex(
|
||||
r'/([a-z]{2})_', cc_url, 'lang',
|
||||
default=cc_label.split()[0] if cc_label else 'en')
|
||||
original_lang = self._search_regex(
|
||||
r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang',
|
||||
default=None)
|
||||
sub_dict = (automatic_captions
|
||||
if 'auto-translated' in cc_label or original_lang
|
||||
else subtitles)
|
||||
sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({
|
||||
'url': cc_url,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': lecture_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'automatic_captions': automatic_captions,
|
||||
}
|
||||
|
||||
|
||||
class LecturioCourseIE(LecturioBaseIE):
|
||||
_VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
|
||||
_TEST = {
|
||||
'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
|
||||
'info_dict': {
|
||||
'id': 'microbiology-introduction',
|
||||
'title': 'Microbiology: Introduction',
|
||||
},
|
||||
'playlist_count': 45,
|
||||
'skip': 'Requires lecturio account credentials',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
entries = []
|
||||
for mobj in re.finditer(
|
||||
r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
|
||||
webpage):
|
||||
params = extract_attributes(mobj.group(0))
|
||||
lecture_url = urljoin(url, params.get('data-url'))
|
||||
lecture_id = params.get('data-id')
|
||||
entries.append(self.url_result(
|
||||
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
|
||||
|
||||
title = self._search_regex(
|
||||
r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
|
||||
'title', default=None)
|
||||
|
||||
return self.playlist_result(entries, display_id, title)
|
||||
|
||||
|
||||
class LecturioDeCourseIE(LecturioBaseIE):
|
||||
_VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs'
|
||||
_TEST = {
|
||||
'url': 'https://www.lecturio.de/jura/grundrechte.kurs',
|
||||
'only_matching': True,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
entries = []
|
||||
for mobj in re.finditer(
|
||||
r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>',
|
||||
webpage):
|
||||
lecture_url = urljoin(url, mobj.group('url'))
|
||||
lecture_id = mobj.group('id')
|
||||
entries.append(self.url_result(
|
||||
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
|
||||
|
||||
title = self._search_regex(
|
||||
r'<h1[^>]*>([^<]+)', webpage, 'title', default=None)
|
||||
|
||||
return self.playlist_result(entries, display_id, title)
|
||||
@ -87,7 +87,7 @@ class LiveLeakIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
|
||||
r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"',
|
||||
webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -120,13 +120,27 @@ class LiveLeakIE(InfoExtractor):
|
||||
}
|
||||
|
||||
for idx, info_dict in enumerate(entries):
|
||||
formats = []
|
||||
for a_format in info_dict['formats']:
|
||||
if not a_format.get('height'):
|
||||
a_format['height'] = int_or_none(self._search_regex(
|
||||
r'([0-9]+)p\.mp4', a_format['url'], 'height label',
|
||||
default=None))
|
||||
formats.append(a_format)
|
||||
|
||||
self._sort_formats(info_dict['formats'])
|
||||
# Removing '.*.mp4' gives the raw video, which is essentially
|
||||
# the same video without the LiveLeak logo at the top (see
|
||||
# https://github.com/rg3/youtube-dl/pull/4768)
|
||||
orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url'])
|
||||
if a_format['url'] != orig_url:
|
||||
format_id = a_format.get('format_id')
|
||||
formats.append({
|
||||
'format_id': 'original' + ('-' + format_id if format_id else ''),
|
||||
'url': orig_url,
|
||||
'preference': 1,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
info_dict['formats'] = formats
|
||||
|
||||
# Don't append entry ID for one-video pages to keep backward compatibility
|
||||
if len(entries) > 1:
|
||||
@ -146,7 +160,7 @@ class LiveLeakIE(InfoExtractor):
|
||||
|
||||
|
||||
class LiveLeakEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[ift])=(?P<id>[\w_]+)'
|
||||
|
||||
# See generic.py for actual test cases
|
||||
_TESTS = [{
|
||||
@ -158,15 +172,14 @@ class LiveLeakEmbedIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
kind, video_id = mobj.group('kind', 'id')
|
||||
kind, video_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
if kind == 'f':
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
liveleak_url = self._search_regex(
|
||||
r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
|
||||
r'(?:logourl\s*:\s*|window\.open\()(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
|
||||
webpage, 'LiveLeak URL', group='url')
|
||||
elif kind == 'i':
|
||||
liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id
|
||||
else:
|
||||
liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id)
|
||||
|
||||
return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())
|
||||
|
||||
@ -15,7 +15,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class LyndaBaseIE(InfoExtractor):
|
||||
_SIGNIN_URL = 'https://www.lynda.com/signin'
|
||||
_SIGNIN_URL = 'https://www.lynda.com/signin/lynda'
|
||||
_PASSWORD_URL = 'https://www.lynda.com/signin/password'
|
||||
_USER_URL = 'https://www.lynda.com/signin/user'
|
||||
_ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
|
||||
|
||||
@ -21,7 +21,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class MediasiteIE(InfoExtractor):
|
||||
_VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
|
||||
_VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
|
||||
@ -84,7 +84,15 @@ class MediasiteIE(InfoExtractor):
|
||||
'timestamp': 1333983600,
|
||||
'duration': 7794,
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d',
|
||||
'only_matching': True,
|
||||
},
|
||||
]
|
||||
|
||||
# look in Mediasite.Core.js (Mediasite.ContentStreamType[*])
|
||||
|
||||
@ -211,13 +211,13 @@ class NRKIE(NRKBaseIE):
|
||||
_TESTS = [{
|
||||
# video
|
||||
'url': 'http://www.nrk.no/video/PS*150533',
|
||||
'md5': '2f7f6eeb2aacdd99885f355428715cfa',
|
||||
'md5': '706f34cdf1322577589e369e522b50ef',
|
||||
'info_dict': {
|
||||
'id': '150533',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dompap og andre fugler i Piip-Show',
|
||||
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
|
||||
'duration': 263,
|
||||
'duration': 262,
|
||||
}
|
||||
}, {
|
||||
# audio
|
||||
@ -248,7 +248,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:tv|radio)\.nrk(?:super)?\.no/
|
||||
(?:serie/[^/]+|program)/
|
||||
(?:serie(?:/[^/]+){1,2}|program)/
|
||||
(?![Ee]pisodes)%s
|
||||
(?:/\d{2}-\d{2}-\d{4})?
|
||||
(?:\#del=(?P<part_id>\d+))?
|
||||
@ -256,14 +256,14 @@ class NRKTVIE(NRKBaseIE):
|
||||
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
|
||||
_TESTS = [{
|
||||
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
|
||||
'md5': '4e9ca6629f09e588ed240fb11619922a',
|
||||
'md5': '9a167e54d04671eb6317a37b7bc8a280',
|
||||
'info_dict': {
|
||||
'id': 'MUHH48000314AA',
|
||||
'ext': 'mp4',
|
||||
'title': '20 spørsmål 23.05.2014',
|
||||
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
|
||||
'duration': 1741,
|
||||
'series': '20 spørsmål - TV',
|
||||
'series': '20 spørsmål',
|
||||
'episode': '23.05.2014',
|
||||
},
|
||||
}, {
|
||||
@ -301,7 +301,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
'id': 'MSPO40010515AH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
|
||||
'description': 'md5:c03aba1e917561eface5214020551b7a',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 772,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
@ -314,7 +314,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
'id': 'MSPO40010515BH',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
|
||||
'description': 'md5:c03aba1e917561eface5214020551b7a',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
'duration': 6175,
|
||||
'series': 'Tour de Ski',
|
||||
'episode': '06.01.2015',
|
||||
@ -326,7 +326,7 @@ class NRKTVIE(NRKBaseIE):
|
||||
'info_dict': {
|
||||
'id': 'MSPO40010515',
|
||||
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
|
||||
'description': 'md5:c03aba1e917561eface5214020551b7a',
|
||||
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
|
||||
},
|
||||
'expected_warnings': ['Video is geo restricted'],
|
||||
}, {
|
||||
@ -362,6 +362,9 @@ class NRKTVIE(NRKBaseIE):
|
||||
}, {
|
||||
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
@ -403,21 +406,35 @@ class NRKTVSerieBaseIE(InfoExtractor):
|
||||
def _extract_series(self, webpage, display_id, fatal=True):
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config',
|
||||
default='{}' if not fatal else NO_DEFAULT),
|
||||
(r'INITIAL_DATA_*\s*=\s*({.+?})\s*;',
|
||||
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
|
||||
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
|
||||
display_id, fatal=False)
|
||||
if not config:
|
||||
return
|
||||
return try_get(config, lambda x: x['series'], dict)
|
||||
return try_get(
|
||||
config,
|
||||
(lambda x: x['initialState']['series'], lambda x: x['series']),
|
||||
dict)
|
||||
|
||||
def _extract_seasons(self, seasons):
|
||||
if not isinstance(seasons, list):
|
||||
return []
|
||||
entries = []
|
||||
for season in seasons:
|
||||
entries.extend(self._extract_episodes(season))
|
||||
return entries
|
||||
|
||||
def _extract_episodes(self, season):
|
||||
entries = []
|
||||
if not isinstance(season, dict):
|
||||
return entries
|
||||
episodes = season.get('episodes')
|
||||
if not isinstance(episodes, list):
|
||||
return entries
|
||||
for episode in episodes:
|
||||
return []
|
||||
return self._extract_entries(season.get('episodes'))
|
||||
|
||||
def _extract_entries(self, entry_list):
|
||||
if not isinstance(entry_list, list):
|
||||
return []
|
||||
entries = []
|
||||
for episode in entry_list:
|
||||
nrk_id = episode.get('prfId')
|
||||
if not nrk_id or not isinstance(nrk_id, compat_str):
|
||||
continue
|
||||
@ -462,7 +479,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
||||
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
|
||||
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
# new layout
|
||||
# new layout, seasons
|
||||
'url': 'https://tv.nrk.no/serie/backstage',
|
||||
'info_dict': {
|
||||
'id': 'backstage',
|
||||
@ -471,20 +488,21 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
||||
},
|
||||
'playlist_mincount': 60,
|
||||
}, {
|
||||
# old layout
|
||||
# new layout, instalments
|
||||
'url': 'https://tv.nrk.no/serie/groenn-glede',
|
||||
'info_dict': {
|
||||
'id': 'groenn-glede',
|
||||
'title': 'Grønn glede',
|
||||
'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
|
||||
},
|
||||
'playlist_mincount': 9,
|
||||
'playlist_mincount': 10,
|
||||
}, {
|
||||
'url': 'http://tv.nrksuper.no/serie/labyrint',
|
||||
# old layout
|
||||
'url': 'https://tv.nrksuper.no/serie/labyrint',
|
||||
'info_dict': {
|
||||
'id': 'labyrint',
|
||||
'title': 'Labyrint',
|
||||
'description': 'md5:58afd450974c89e27d5a19212eee7115',
|
||||
'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
|
||||
},
|
||||
'playlist_mincount': 3,
|
||||
}, {
|
||||
@ -517,11 +535,12 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
||||
description = try_get(
|
||||
series, lambda x: x['titles']['subtitle'], compat_str)
|
||||
entries = []
|
||||
for season in series['seasons']:
|
||||
entries.extend(self._extract_episodes(season))
|
||||
entries.extend(self._extract_seasons(series.get('seasons')))
|
||||
entries.extend(self._extract_entries(series.get('instalments')))
|
||||
entries.extend(self._extract_episodes(series.get('extraMaterial')))
|
||||
return self.playlist_result(entries, series_id, title, description)
|
||||
|
||||
# Old layout (e.g. https://tv.nrk.no/serie/groenn-glede)
|
||||
# Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
|
||||
entries = [
|
||||
self.url_result(
|
||||
'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
|
||||
@ -533,6 +552,9 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
|
||||
'seriestitle', webpage,
|
||||
'title', default=None) or self._og_search_title(
|
||||
webpage, fatal=False)
|
||||
if title:
|
||||
title = self._search_regex(
|
||||
r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title)
|
||||
|
||||
description = self._html_search_meta(
|
||||
'series_description', webpage,
|
||||
@ -593,7 +615,7 @@ class NRKPlaylistIE(NRKPlaylistBaseIE):
|
||||
'title': 'Rivertonprisen til Karin Fossum',
|
||||
'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
|
||||
},
|
||||
'playlist_count': 5,
|
||||
'playlist_count': 2,
|
||||
}]
|
||||
|
||||
def _extract_title(self, webpage):
|
||||
|
||||
@ -27,7 +27,7 @@ class PornHubIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
|
||||
(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
|
||||
(?:www\.)?thumbzilla\.com/video/
|
||||
)
|
||||
(?P<id>[\da-z]+)
|
||||
@ -129,7 +129,7 @@ class PornHubIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
|
||||
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
|
||||
webpage)
|
||||
|
||||
def _extract_count(self, pattern, webpage, name):
|
||||
@ -137,14 +137,16 @@ class PornHubIE(InfoExtractor):
|
||||
pattern, webpage, '%s count' % name, fatal=False))
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host') or 'pornhub.com'
|
||||
video_id = mobj.group('id')
|
||||
|
||||
self._set_cookie('pornhub.com', 'age_verified', '1')
|
||||
self._set_cookie(host, 'age_verified', '1')
|
||||
|
||||
def dl_webpage(platform):
|
||||
self._set_cookie('pornhub.com', 'platform', platform)
|
||||
self._set_cookie(host, 'platform', platform)
|
||||
return self._download_webpage(
|
||||
'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
|
||||
'http://www.%s/view_video.php?viewkey=%s' % (host, video_id),
|
||||
video_id, 'Downloading %s webpage' % platform)
|
||||
|
||||
webpage = dl_webpage('pc')
|
||||
@ -306,7 +308,7 @@ class PornHubIE(InfoExtractor):
|
||||
|
||||
|
||||
class PornHubPlaylistBaseIE(InfoExtractor):
|
||||
def _extract_entries(self, webpage):
|
||||
def _extract_entries(self, webpage, host):
|
||||
# Only process container div with main playlist content skipping
|
||||
# drop-down menu that uses similar pattern for videos (see
|
||||
# https://github.com/rg3/youtube-dl/issues/11594).
|
||||
@ -316,7 +318,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
|
||||
|
||||
return [
|
||||
self.url_result(
|
||||
'http://www.pornhub.com/%s' % video_url,
|
||||
'http://www.%s/%s' % (host, video_url),
|
||||
PornHubIE.ie_key(), video_title=title)
|
||||
for video_url, title in orderedSet(re.findall(
|
||||
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
|
||||
@ -324,11 +326,13 @@ class PornHubPlaylistBaseIE(InfoExtractor):
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
playlist_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
entries = self._extract_entries(webpage)
|
||||
entries = self._extract_entries(webpage, host)
|
||||
|
||||
playlist = self._parse_json(
|
||||
self._search_regex(
|
||||
@ -343,7 +347,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
|
||||
|
||||
|
||||
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
|
||||
_VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/playlist/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.pornhub.com/playlist/4667351',
|
||||
'info_dict': {
|
||||
@ -358,7 +362,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
|
||||
|
||||
|
||||
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
|
||||
_VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
|
||||
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
|
||||
'info_dict': {
|
||||
@ -399,7 +403,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
user_id = mobj.group('id')
|
||||
|
||||
entries = []
|
||||
for page_num in itertools.count(1):
|
||||
@ -411,7 +417,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
||||
break
|
||||
raise
|
||||
page_entries = self._extract_entries(webpage)
|
||||
page_entries = self._extract_entries(webpage, host)
|
||||
if not page_entries:
|
||||
break
|
||||
entries.extend(page_entries)
|
||||
|
||||
@ -15,10 +15,10 @@ from ..utils import (
|
||||
|
||||
|
||||
class SafariBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
|
||||
_LOGIN_URL = 'https://learning.oreilly.com/accounts/login/'
|
||||
_NETRC_MACHINE = 'safari'
|
||||
|
||||
_API_BASE = 'https://www.safaribooksonline.com/api/v1'
|
||||
_API_BASE = 'https://learning.oreilly.com/api/v1'
|
||||
_API_FORMAT = 'json'
|
||||
|
||||
LOGGED_IN = False
|
||||
@ -76,7 +76,7 @@ class SafariIE(SafariBaseIE):
|
||||
IE_DESC = 'safaribooksonline.com online video'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.)?safaribooksonline\.com/
|
||||
(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
|
||||
(?:
|
||||
library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
|
||||
videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
|
||||
@ -104,6 +104,9 @@ class SafariIE(SafariBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_PARTNER_ID = '1926081'
|
||||
@ -160,7 +163,7 @@ class SafariIE(SafariBaseIE):
|
||||
|
||||
class SafariApiIE(SafariBaseIE):
|
||||
IE_NAME = 'safari:api'
|
||||
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
|
||||
@ -185,7 +188,7 @@ class SafariCourseIE(SafariBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?safaribooksonline\.com/
|
||||
(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
|
||||
(?:
|
||||
library/view/[^/]+|
|
||||
api/v1/book|
|
||||
@ -213,6 +216,9 @@ class SafariCourseIE(SafariBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
|
||||
@ -19,7 +19,7 @@ class ScrippsNetworksWatchIE(AWSIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
watch\.
|
||||
(?P<site>hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/
|
||||
(?P<site>geniuskitchen)\.com/
|
||||
(?:
|
||||
player\.[A-Z0-9]+\.html\#|
|
||||
show/(?:[^/]+/){2}|
|
||||
@ -28,38 +28,23 @@ class ScrippsNetworksWatchIE(AWSIE):
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/',
|
||||
'md5': '26545fd676d939954c6808274bdb905a',
|
||||
'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/',
|
||||
'info_dict': {
|
||||
'id': '4173834',
|
||||
'id': '4194875',
|
||||
'ext': 'mp4',
|
||||
'title': 'Best Ever Treehouses',
|
||||
'description': "We're searching for the most over the top treehouses.",
|
||||
'title': 'Ample Hills Ice Cream Bike',
|
||||
'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.',
|
||||
'uploader': 'ANV',
|
||||
'upload_date': '20170922',
|
||||
'timestamp': 1506056400,
|
||||
'upload_date': '20171011',
|
||||
'timestamp': 1507698000,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': [AnvatoIE.ie_key()],
|
||||
}, {
|
||||
'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://watch.diynetwork.com/player.HNT.html#2656646',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_SNI_TABLE = {
|
||||
'hgtv': 'hgtv',
|
||||
'diynetwork': 'diy',
|
||||
'foodnetwork': 'food',
|
||||
'cookingchanneltv': 'cook',
|
||||
'travelchannel': 'trav',
|
||||
'geniuskitchen': 'genius',
|
||||
}
|
||||
|
||||
|
||||
@ -16,7 +16,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class TBSIE(TurnerBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
|
||||
'info_dict': {
|
||||
@ -40,12 +40,12 @@ class TBSIE(TurnerBaseIE):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
site, display_id = re.match(self._VALID_URL, url).groups()
|
||||
site, path, display_id = re.match(self._VALID_URL, url).groups()
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
drupal_settings = self._parse_json(self._search_regex(
|
||||
r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>',
|
||||
webpage, 'drupal setting'), display_id)
|
||||
video_data = drupal_settings['turner_playlist'][0]
|
||||
video_data = next(v for v in drupal_settings['turner_playlist'] if v.get('url') == path)
|
||||
|
||||
media_id = video_data['mediaID']
|
||||
title = video_data['title']
|
||||
|
||||
@ -14,20 +14,38 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class UpskillBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'http://upskillcourses.com/sign_in'
|
||||
_NETRC_MACHINE = 'upskill'
|
||||
class TeachableBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'teachable'
|
||||
_URL_PREFIX = 'teachable:'
|
||||
|
||||
_SITES = {
|
||||
# Only notable ones here
|
||||
'upskillcourses.com': 'upskill',
|
||||
'academy.gns3.com': 'gns3',
|
||||
'academyhacker.com': 'academyhacker',
|
||||
'stackskills.com': 'stackskills',
|
||||
'market.saleshacker.com': 'saleshacker',
|
||||
'learnability.org': 'learnability',
|
||||
'edurila.com': 'edurila',
|
||||
}
|
||||
|
||||
_VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
self._logged_in = False
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
def _login(self, site):
|
||||
if self._logged_in:
|
||||
return
|
||||
|
||||
username, password = self._get_login_info(
|
||||
netrc_machine=self._SITES.get(site, site))
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_page, urlh = self._download_webpage_handle(
|
||||
self._LOGIN_URL, None, 'Downloading login page')
|
||||
'https://%s/sign_in' % site, None,
|
||||
'Downloading %s login page' % site)
|
||||
|
||||
login_url = compat_str(urlh.geturl())
|
||||
|
||||
@ -46,18 +64,24 @@ class UpskillBaseIE(InfoExtractor):
|
||||
post_url = urljoin(login_url, post_url)
|
||||
|
||||
response = self._download_webpage(
|
||||
post_url, None, 'Logging in',
|
||||
post_url, None, 'Logging in to %s' % site,
|
||||
data=urlencode_postdata(login_form),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
'Referer': login_url,
|
||||
})
|
||||
|
||||
if '>I accept the new Privacy Policy<' in response:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s asks you to accept new Privacy Policy. '
|
||||
'Go to https://%s/ and accept.' % (site, site), expected=True)
|
||||
|
||||
# Successful login
|
||||
if any(re.search(p, response) for p in (
|
||||
r'class=["\']user-signout',
|
||||
r'<a[^>]+\bhref=["\']/sign_out',
|
||||
r'>\s*Log out\s*<')):
|
||||
self._logged_in = True
|
||||
return
|
||||
|
||||
message = get_element_by_class('alert', response)
|
||||
@ -68,8 +92,14 @@ class UpskillBaseIE(InfoExtractor):
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
|
||||
class UpskillIE(UpskillBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P<id>\d+)'
|
||||
class TeachableIE(TeachableBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
%shttps?://(?P<site_t>[^/]+)|
|
||||
https?://(?:www\.)?(?P<site>%s)
|
||||
)
|
||||
/courses/[^/]+/lectures/(?P<id>\d+)
|
||||
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
|
||||
@ -77,7 +107,7 @@ class UpskillIE(UpskillBaseIE):
|
||||
'id': 'uzw6zw58or',
|
||||
'ext': 'mp4',
|
||||
'title': 'Welcome to the Course!',
|
||||
'description': 'md5:8d66c13403783370af62ca97a7357bdd',
|
||||
'description': 'md5:65edb0affa582974de4625b9cdea1107',
|
||||
'duration': 138.763,
|
||||
'timestamp': 1479846621,
|
||||
'upload_date': '20161122',
|
||||
@ -88,10 +118,37 @@ class UpskillIE(UpskillBaseIE):
|
||||
}, {
|
||||
'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _is_teachable(webpage):
|
||||
return 'teachableTracker.linker:autoLink' in webpage and re.search(
|
||||
r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
|
||||
webpage)
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(webpage, source_url):
|
||||
if not TeachableIE._is_teachable(webpage):
|
||||
return
|
||||
if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
|
||||
return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
site = mobj.group('site') or mobj.group('site_t')
|
||||
video_id = mobj.group('id')
|
||||
|
||||
self._login(site)
|
||||
|
||||
prefixed = url.startswith(self._URL_PREFIX)
|
||||
if prefixed:
|
||||
url = url[len(self._URL_PREFIX):]
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
@ -113,12 +170,18 @@ class UpskillIE(UpskillBaseIE):
|
||||
}
|
||||
|
||||
|
||||
class UpskillCourseIE(UpskillBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P<id>[^/?#&]+)'
|
||||
class TeachableCourseIE(TeachableBaseIE):
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
%shttps?://(?P<site_t>[^/]+)|
|
||||
https?://(?:www\.)?(?P<site>%s)
|
||||
)
|
||||
/(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
|
||||
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
|
||||
_TESTS = [{
|
||||
'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
|
||||
'info_dict': {
|
||||
'id': '119763',
|
||||
'id': 'essential-web-developer-course',
|
||||
'title': 'The Essential Web Developer Course (Free)',
|
||||
},
|
||||
'playlist_count': 192,
|
||||
@ -128,21 +191,37 @@ class UpskillCourseIE(UpskillBaseIE):
|
||||
}, {
|
||||
'url': 'http://upskillcourses.com/courses/enrolled/119763',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://academy.gns3.com/courses/enrolled/423415',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if UpskillIE.suitable(url) else super(
|
||||
UpskillCourseIE, cls).suitable(url)
|
||||
return False if TeachableIE.suitable(url) else super(
|
||||
TeachableCourseIE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
course_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
site = mobj.group('site') or mobj.group('site_t')
|
||||
course_id = mobj.group('id')
|
||||
|
||||
self._login(site)
|
||||
|
||||
prefixed = url.startswith(self._URL_PREFIX)
|
||||
if prefixed:
|
||||
prefix = self._URL_PREFIX
|
||||
url = url[len(prefix):]
|
||||
|
||||
webpage = self._download_webpage(url, course_id)
|
||||
|
||||
course_id = self._search_regex(
|
||||
r'data-course-id=["\'](\d+)', webpage, 'course id',
|
||||
default=course_id)
|
||||
url_base = 'https://%s/' % site
|
||||
|
||||
entries = []
|
||||
|
||||
@ -162,10 +241,13 @@ class UpskillCourseIE(UpskillBaseIE):
|
||||
title = self._html_search_regex(
|
||||
r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
|
||||
'title', default=None)
|
||||
entry_url = urljoin(url_base, lecture_url)
|
||||
if prefixed:
|
||||
entry_url = self._URL_PREFIX + entry_url
|
||||
entries.append(
|
||||
self.url_result(
|
||||
urljoin('http://upskillcourses.com/', lecture_url),
|
||||
ie=UpskillIE.ie_key(), video_id=lecture_id,
|
||||
entry_url,
|
||||
ie=TeachableIE.ie_key(), video_id=lecture_id,
|
||||
video_title=clean_html(title)))
|
||||
|
||||
course_title = self._html_search_regex(
|
||||
117
youtube_dl/extractor/tiktok.py
Normal file
117
youtube_dl/extractor/tiktok.py
Normal file
@ -0,0 +1,117 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_str,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
try_get,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class TikTokBaseIE(InfoExtractor):
|
||||
def _extract_aweme(self, data):
|
||||
video = data['video']
|
||||
description = str_or_none(try_get(data, lambda x: x['desc']))
|
||||
width = int_or_none(try_get(data, lambda x: video['width']))
|
||||
height = int_or_none(try_get(data, lambda x: video['height']))
|
||||
|
||||
format_urls = set()
|
||||
formats = []
|
||||
for format_id in (
|
||||
'play_addr_lowbr', 'play_addr', 'play_addr_h264',
|
||||
'download_addr'):
|
||||
for format in try_get(
|
||||
video, lambda x: x[format_id]['url_list'], list) or []:
|
||||
format_url = url_or_none(format)
|
||||
if not format_url:
|
||||
continue
|
||||
if format_url in format_urls:
|
||||
continue
|
||||
format_urls.add(format_url)
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'ext': 'mp4',
|
||||
'height': height,
|
||||
'width': width,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = url_or_none(try_get(
|
||||
video, lambda x: x['cover']['url_list'][0], compat_str))
|
||||
uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
|
||||
timestamp = int_or_none(data.get('create_time'))
|
||||
comment_count = int_or_none(data.get('comment_count')) or int_or_none(
|
||||
try_get(data, lambda x: x['statistics']['comment_count']))
|
||||
repost_count = int_or_none(try_get(
|
||||
data, lambda x: x['statistics']['share_count']))
|
||||
|
||||
aweme_id = data['aweme_id']
|
||||
|
||||
return {
|
||||
'id': aweme_id,
|
||||
'title': uploader or aweme_id,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'timestamp': timestamp,
|
||||
'comment_count': comment_count,
|
||||
'repost_count': repost_count,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class TikTokIE(TikTokBaseIE):
|
||||
_VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://m.tiktok.com/v/6606727368545406213.html',
|
||||
'md5': 'd584b572e92fcd48888051f238022420',
|
||||
'info_dict': {
|
||||
'id': '6606727368545406213',
|
||||
'ext': 'mp4',
|
||||
'title': 'Zureeal',
|
||||
'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
|
||||
'thumbnail': r're:^https?://.*~noop.image',
|
||||
'uploader': 'Zureeal',
|
||||
'timestamp': 1538248586,
|
||||
'upload_date': '20180929',
|
||||
'comment_count': int,
|
||||
'repost_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id)
|
||||
return self._extract_aweme(data)
|
||||
|
||||
|
||||
class TikTokUserIE(TikTokBaseIE):
|
||||
_VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html',
|
||||
'info_dict': {
|
||||
'id': '188294915489964032',
|
||||
},
|
||||
'playlist_mincount': 24,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id = self._match_id(url)
|
||||
data = self._download_json(
|
||||
'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id,
|
||||
query={'_signature': '_'})
|
||||
entries = []
|
||||
for aweme in data['aweme_list']:
|
||||
try:
|
||||
entry = self._extract_aweme(aweme)
|
||||
except ExtractorError:
|
||||
continue
|
||||
entry['extractor_key'] = TikTokIE.ie_key()
|
||||
entries.append(entry)
|
||||
return self.playlist_result(entries, user_id)
|
||||
@ -171,7 +171,8 @@ class TwitterCardIE(TwitterBaseIE):
|
||||
urls.append('https://twitter.com/i/videos/' + video_id)
|
||||
|
||||
for u in urls:
|
||||
webpage = self._download_webpage(u, video_id)
|
||||
webpage = self._download_webpage(
|
||||
u, video_id, headers={'Referer': 'https://twitter.com/'})
|
||||
|
||||
iframe_url = self._html_search_regex(
|
||||
r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
|
||||
|
||||
@ -61,7 +61,7 @@ class UOLIE(InfoExtractor):
|
||||
'height': 360,
|
||||
},
|
||||
'5': {
|
||||
'width': 1080,
|
||||
'width': 1280,
|
||||
'height': 720,
|
||||
},
|
||||
'6': {
|
||||
@ -80,6 +80,10 @@ class UOLIE(InfoExtractor):
|
||||
'width': 568,
|
||||
'height': 320,
|
||||
},
|
||||
'11': {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -111,19 +115,31 @@ class UOLIE(InfoExtractor):
|
||||
'ver': video_data.get('numRevision', 2),
|
||||
'r': 'http://mais.uol.com.br',
|
||||
}
|
||||
for k in ('token', 'sign'):
|
||||
v = video_data.get(k)
|
||||
if v:
|
||||
query[k] = v
|
||||
|
||||
formats = []
|
||||
for f in video_data.get('formats', []):
|
||||
f_url = f.get('url') or f.get('secureUrl')
|
||||
if not f_url:
|
||||
continue
|
||||
f_url = update_url_query(f_url, query)
|
||||
format_id = str_or_none(f.get('id'))
|
||||
if format_id == '10':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
f_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
continue
|
||||
fmt = {
|
||||
'format_id': format_id,
|
||||
'url': update_url_query(f_url, query),
|
||||
'url': f_url,
|
||||
'source_preference': 1,
|
||||
}
|
||||
fmt.update(self._FORMATS.get(format_id, {}))
|
||||
formats.append(fmt)
|
||||
self._sort_formats(formats)
|
||||
self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext'))
|
||||
|
||||
tags = []
|
||||
for tag in video_data.get('tags', []):
|
||||
|
||||
@ -14,10 +14,13 @@ from ..compat import (
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
js_to_json,
|
||||
InAdvancePagedList,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
NO_DEFAULT,
|
||||
parse_filesize,
|
||||
qualities,
|
||||
RegexNotFoundError,
|
||||
sanitized_Request,
|
||||
smuggle_url,
|
||||
@ -27,7 +30,6 @@ from ..utils import (
|
||||
unsmuggle_url,
|
||||
urlencode_postdata,
|
||||
unescapeHTML,
|
||||
parse_filesize,
|
||||
)
|
||||
|
||||
|
||||
@ -1063,3 +1065,96 @@ class VimeoLikesIE(InfoExtractor):
|
||||
'description': description,
|
||||
'entries': pl,
|
||||
}
|
||||
|
||||
|
||||
class VHXEmbedIE(InfoExtractor):
|
||||
IE_NAME = 'vhx:embed'
|
||||
_VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
|
||||
|
||||
def _call_api(self, video_id, access_token, path='', query=None):
|
||||
return self._download_json(
|
||||
'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={
|
||||
'Authorization': 'Bearer ' + access_token,
|
||||
}, query=query)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
credentials = self._parse_json(self._search_regex(
|
||||
r'(?s)credentials\s*:\s*({.+?}),', webpage,
|
||||
'config'), video_id, js_to_json)
|
||||
access_token = credentials['access_token']
|
||||
|
||||
query = {}
|
||||
for k, v in credentials.items():
|
||||
if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined':
|
||||
if k == 'authUserToken':
|
||||
query['auth_user_token'] = v
|
||||
else:
|
||||
query[k] = v
|
||||
files = self._call_api(video_id, access_token, '/files', query)
|
||||
|
||||
formats = []
|
||||
for f in files:
|
||||
href = try_get(f, lambda x: x['_links']['source']['href'])
|
||||
if not href:
|
||||
continue
|
||||
method = f.get('method')
|
||||
if method == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
href, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif method == 'dash':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
href, video_id, mpd_id='dash', fatal=False))
|
||||
else:
|
||||
fmt = {
|
||||
'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])),
|
||||
'format_id': 'http',
|
||||
'preference': 1,
|
||||
'url': href,
|
||||
'vcodec': f.get('codec'),
|
||||
}
|
||||
quality = f.get('quality')
|
||||
if quality:
|
||||
fmt.update({
|
||||
'format_id': 'http-' + quality,
|
||||
'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)),
|
||||
})
|
||||
formats.append(fmt)
|
||||
self._sort_formats(formats)
|
||||
|
||||
video_data = self._call_api(video_id, access_token)
|
||||
title = video_data.get('title') or video_data['name']
|
||||
|
||||
subtitles = {}
|
||||
for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []:
|
||||
lang = subtitle.get('srclang') or subtitle.get('label')
|
||||
for _link in subtitle.get('_links', {}).values():
|
||||
href = _link.get('href')
|
||||
if not href:
|
||||
continue
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': href,
|
||||
})
|
||||
|
||||
q = qualities(['small', 'medium', 'large', 'source'])
|
||||
thumbnails = []
|
||||
for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items():
|
||||
thumbnails.append({
|
||||
'id': thumbnail_id,
|
||||
'url': thumbnail_url,
|
||||
'preference': q(thumbnail_id),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': video_data.get('description'),
|
||||
'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])),
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': unified_timestamp(video_data.get('created_at')),
|
||||
'view_count': int_or_none(video_data.get('plays_count')),
|
||||
}
|
||||
|
||||
@ -120,8 +120,10 @@ class VRVIE(VRVBaseIE):
|
||||
url, video_id,
|
||||
headers=self.geo_verification_headers())
|
||||
media_resource = self._parse_json(self._search_regex(
|
||||
r'window\.__INITIAL_STATE__\s*=\s*({.+?})</script>',
|
||||
webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
|
||||
[
|
||||
r'window\.__INITIAL_STATE__\s*=\s*({.+?})(?:</script>|;)',
|
||||
r'window\.__INITIAL_STATE__\s*=\s*({.+})'
|
||||
], webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
|
||||
|
||||
video_data = media_resource.get('json')
|
||||
if not video_data:
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class WistiaIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.net/embed/iframe/)(?P<id>[a-z0-9]+)'
|
||||
_VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/iframe/)(?P<id>[a-z0-9]+)'
|
||||
_API_URL = 'http://fast.wistia.com/embed/medias/%s.json'
|
||||
_IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s'
|
||||
|
||||
@ -35,12 +35,15 @@ class WistiaIE(InfoExtractor):
|
||||
# with hls video
|
||||
'url': 'wistia:807fafadvk',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(webpage):
|
||||
match = re.search(
|
||||
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
|
||||
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage)
|
||||
if match:
|
||||
return unescapeHTML(match.group('url'))
|
||||
|
||||
|
||||
@ -45,7 +45,7 @@ class XVideosIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://www.xvideos.com/video%s/' % video_id, video_id)
|
||||
'https://www.xvideos.com/video%s/' % video_id, video_id)
|
||||
|
||||
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
|
||||
if mobj:
|
||||
|
||||
@ -26,7 +26,7 @@ class YourPornIE(InfoExtractor):
|
||||
self._search_regex(
|
||||
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
|
||||
group='data'),
|
||||
video_id)[video_id])
|
||||
video_id)[video_id]).replace('/cdn/', '/cdn2/')
|
||||
|
||||
title = (self._search_regex(
|
||||
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
|
||||
|
||||
@ -48,6 +48,7 @@ from ..utils import (
|
||||
unified_strdate,
|
||||
unsmuggle_url,
|
||||
uppercase_escape,
|
||||
url_or_none,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
@ -1104,7 +1105,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
def _extract_signature_function(self, video_id, player_url, example_sig):
|
||||
id_m = re.match(
|
||||
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
|
||||
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
|
||||
player_url)
|
||||
if not id_m:
|
||||
raise ExtractorError('Cannot identify player %r' % player_url)
|
||||
@ -1386,8 +1387,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
self._downloader.report_warning(err_msg)
|
||||
return {}
|
||||
|
||||
def _mark_watched(self, video_id, video_info):
|
||||
playback_url = video_info.get('videostats_playback_base_url', [None])[0]
|
||||
def _mark_watched(self, video_id, video_info, player_response):
|
||||
playback_url = url_or_none(try_get(
|
||||
player_response,
|
||||
lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
|
||||
video_info, lambda x: x['videostats_playback_base_url'][0]))
|
||||
if not playback_url:
|
||||
return
|
||||
parsed_playback_url = compat_urlparse.urlparse(playback_url)
|
||||
@ -1712,30 +1716,36 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
else:
|
||||
video_description = ''
|
||||
|
||||
if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
|
||||
if not smuggled_data.get('force_singlefeed', False):
|
||||
if not self._downloader.params.get('noplaylist'):
|
||||
entries = []
|
||||
feed_ids = []
|
||||
multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
|
||||
for feed in multifeed_metadata_list.split(','):
|
||||
# Unquote should take place before split on comma (,) since textual
|
||||
# fields may contain comma as well (see
|
||||
# https://github.com/rg3/youtube-dl/issues/8536)
|
||||
feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Youtube',
|
||||
'url': smuggle_url(
|
||||
'%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
|
||||
{'force_singlefeed': True}),
|
||||
'title': '%s (%s)' % (video_title, feed_data['title'][0]),
|
||||
})
|
||||
feed_ids.append(feed_data['id'][0])
|
||||
self.to_screen(
|
||||
'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
|
||||
% (', '.join(feed_ids), video_id))
|
||||
return self.playlist_result(entries, video_id, video_title, video_description)
|
||||
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
|
||||
multifeed_metadata_list = try_get(
|
||||
player_response,
|
||||
lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
|
||||
compat_str) or try_get(
|
||||
video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
|
||||
if multifeed_metadata_list:
|
||||
entries = []
|
||||
feed_ids = []
|
||||
for feed in multifeed_metadata_list.split(','):
|
||||
# Unquote should take place before split on comma (,) since textual
|
||||
# fields may contain comma as well (see
|
||||
# https://github.com/rg3/youtube-dl/issues/8536)
|
||||
feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': 'Youtube',
|
||||
'url': smuggle_url(
|
||||
'%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
|
||||
{'force_singlefeed': True}),
|
||||
'title': '%s (%s)' % (video_title, feed_data['title'][0]),
|
||||
})
|
||||
feed_ids.append(feed_data['id'][0])
|
||||
self.to_screen(
|
||||
'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
|
||||
% (', '.join(feed_ids), video_id))
|
||||
return self.playlist_result(entries, video_id, video_title, video_description)
|
||||
else:
|
||||
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
|
||||
|
||||
if view_count is None:
|
||||
view_count = extract_view_count(video_info)
|
||||
@ -1824,7 +1834,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
else:
|
||||
player_version = self._search_regex(
|
||||
[r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
|
||||
r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
|
||||
r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
|
||||
player_url,
|
||||
'html5 player', fatal=False)
|
||||
player_desc = 'html5 player %s' % player_version
|
||||
@ -2116,7 +2126,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
self.mark_watched(video_id, video_info)
|
||||
self.mark_watched(video_id, video_info, player_response)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
||||
@ -39,6 +39,7 @@ from .compat import (
|
||||
compat_HTMLParser,
|
||||
compat_basestring,
|
||||
compat_chr,
|
||||
compat_cookiejar,
|
||||
compat_ctypes_WINFUNCTYPE,
|
||||
compat_etree_fromstring,
|
||||
compat_expanduser,
|
||||
@ -1139,6 +1140,33 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
|
||||
req, **kwargs)
|
||||
|
||||
|
||||
class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
|
||||
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
|
||||
# Store session cookies with `expires` set to 0 instead of an empty
|
||||
# string
|
||||
for cookie in self:
|
||||
if cookie.expires is None:
|
||||
cookie.expires = 0
|
||||
compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
|
||||
|
||||
def load(self, filename=None, ignore_discard=False, ignore_expires=False):
|
||||
compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires)
|
||||
# Session cookies are denoted by either `expires` field set to
|
||||
# an empty string or 0. MozillaCookieJar only recognizes the former
|
||||
# (see [1]). So we need force the latter to be recognized as session
|
||||
# cookies on our own.
|
||||
# Session cookies may be important for cookies-based authentication,
|
||||
# e.g. usually, when user does not check 'Remember me' check box while
|
||||
# logging in on a site, some important cookies are stored as session
|
||||
# cookies so that not recognizing them will result in failed login.
|
||||
# 1. https://bugs.python.org/issue17164
|
||||
for cookie in self:
|
||||
# Treat `expires=0` cookies as session cookies
|
||||
if cookie.expires == 0:
|
||||
cookie.expires = None
|
||||
cookie.discard = True
|
||||
|
||||
|
||||
class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
|
||||
def __init__(self, cookiejar=None):
|
||||
compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
|
||||
@ -3948,8 +3976,12 @@ def write_xattr(path, key, value):
|
||||
|
||||
|
||||
def random_birthday(year_field, month_field, day_field):
|
||||
start_date = datetime.date(1950, 1, 1)
|
||||
end_date = datetime.date(1995, 12, 31)
|
||||
offset = random.randint(0, (end_date - start_date).days)
|
||||
random_date = start_date + datetime.timedelta(offset)
|
||||
return {
|
||||
year_field: str(random.randint(1950, 1995)),
|
||||
month_field: str(random.randint(1, 12)),
|
||||
day_field: str(random.randint(1, 31)),
|
||||
year_field: str(random_date.year),
|
||||
month_field: str(random_date.month),
|
||||
day_field: str(random_date.day),
|
||||
}
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2018.11.23'
|
||||
__version__ = '2018.12.17'
|
||||
|
||||
Loading…
Reference in New Issue
Block a user