2013-06-23 19:57:38 +02:00
|
|
|
import base64
|
2014-01-17 14:47:46 +01:00
|
|
|
import hashlib
|
2014-01-07 09:35:34 +01:00
|
|
|
import json
|
2014-07-11 10:57:08 +02:00
|
|
|
import netrc
|
2013-06-23 19:57:38 +02:00
|
|
|
import os
|
|
|
|
import re
|
|
|
|
import socket
|
|
|
|
import sys
|
2014-07-11 10:57:08 +02:00
|
|
|
import time
|
2013-11-24 14:59:19 +01:00
|
|
|
import xml.etree.ElementTree
|
2013-06-23 19:57:38 +02:00
|
|
|
|
|
|
|
from ..utils import (
|
|
|
|
compat_http_client,
|
|
|
|
compat_urllib_error,
|
2013-12-24 23:32:04 +01:00
|
|
|
compat_urllib_parse_urlparse,
|
2013-06-23 19:57:38 +02:00
|
|
|
compat_str,
|
|
|
|
|
|
|
|
clean_html,
|
|
|
|
compiled_regex_type,
|
|
|
|
ExtractorError,
|
2014-07-28 15:25:56 +02:00
|
|
|
int_or_none,
|
2013-10-23 14:38:03 +02:00
|
|
|
RegexNotFoundError,
|
2013-10-28 10:44:02 +01:00
|
|
|
sanitize_filename,
|
2013-07-17 10:38:23 +02:00
|
|
|
unescapeHTML,
|
2013-06-23 19:57:38 +02:00
|
|
|
)
|
2013-12-17 02:49:54 +01:00
|
|
|
_NO_DEFAULT = object()
|
2013-06-23 19:57:38 +02:00
|
|
|
|
2013-11-22 19:57:52 +01:00
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
class InfoExtractor(object):
|
|
|
|
"""Information Extractor class.
|
|
|
|
|
|
|
|
Information extractors are the classes that, given a URL, extract
|
|
|
|
information about the video (or videos) the URL refers to. This
|
|
|
|
information includes the real video URL, the video title, author and
|
|
|
|
others. The information is stored in a dictionary which is then
|
|
|
|
passed to the FileDownloader. The FileDownloader processes this
|
|
|
|
information possibly downloading the video to the file system, among
|
|
|
|
other possible outcomes.
|
|
|
|
|
|
|
|
The dictionaries must include the following fields:
|
|
|
|
|
|
|
|
id: Video identifier.
|
|
|
|
title: Video title, unescaped.
|
2013-12-16 14:13:40 +01:00
|
|
|
|
2013-12-24 11:56:02 +01:00
|
|
|
Additionally, it must contain either a formats entry or a url one:
|
2013-12-16 14:13:40 +01:00
|
|
|
|
2013-12-24 11:56:02 +01:00
|
|
|
formats: A list of dictionaries for each format available, ordered
|
|
|
|
from worst to best quality.
|
|
|
|
|
|
|
|
Potential fields:
|
2013-12-16 14:13:40 +01:00
|
|
|
* url Mandatory. The URL of the video file
|
|
|
|
* ext Will be calculated from url if missing
|
|
|
|
* format A human-readable description of the format
|
|
|
|
("mp4 container with h264/opus").
|
|
|
|
Calculated from the format_id, width, height.
|
|
|
|
and format_note fields if missing.
|
|
|
|
* format_id A short description of the format
|
2013-12-26 21:19:00 +01:00
|
|
|
("mp4_h264_opus" or "19").
|
|
|
|
Technically optional, but strongly recommended.
|
2013-12-16 14:13:40 +01:00
|
|
|
* format_note Additional info about the format
|
|
|
|
("3D" or "DASH video")
|
|
|
|
* width Width of the video, if known
|
|
|
|
* height Height of the video, if known
|
2013-12-24 11:56:02 +01:00
|
|
|
* resolution Textual description of width and height
|
2013-12-25 15:18:40 +01:00
|
|
|
* tbr Average bitrate of audio and video in KBit/s
|
2013-12-16 14:13:40 +01:00
|
|
|
* abr Average audio bitrate in KBit/s
|
|
|
|
* acodec Name of the audio codec in use
|
2014-01-19 05:47:20 +01:00
|
|
|
* asr Audio sampling rate in Hertz
|
2013-12-16 14:13:40 +01:00
|
|
|
* vbr Average video bitrate in KBit/s
|
|
|
|
* vcodec Name of the video codec in use
|
2014-01-23 23:54:06 +01:00
|
|
|
* container Name of the container format
|
2013-12-16 14:13:40 +01:00
|
|
|
* filesize The number of bytes, if known in advance
|
2014-07-21 12:02:44 +02:00
|
|
|
* filesize_approx An estimate for the number of bytes
|
2013-12-16 14:13:40 +01:00
|
|
|
* player_url SWF Player URL (used for rtmpdump).
|
2013-12-24 23:32:04 +01:00
|
|
|
* protocol The protocol that will be used for the actual
|
|
|
|
download, lower-case.
|
2014-01-27 05:47:30 +01:00
|
|
|
"http", "https", "rtsp", "rtmp", "m3u8" or so.
|
2013-12-24 11:56:02 +01:00
|
|
|
* preference Order number of this format. If this field is
|
2014-01-01 20:23:47 +01:00
|
|
|
present and not None, the formats get sorted
|
2014-03-23 17:41:43 +01:00
|
|
|
by this field, regardless of all other values.
|
2013-12-24 11:56:02 +01:00
|
|
|
-1 for default (order by other properties),
|
|
|
|
-2 or smaller for less than default.
|
2014-01-06 17:15:27 +01:00
|
|
|
* quality Order number of the video quality of this
|
|
|
|
format, irrespective of the file format.
|
|
|
|
-1 for default (order by other properties),
|
|
|
|
-2 or smaller for less than default.
|
2014-08-24 01:31:35 +02:00
|
|
|
* http_referer HTTP Referer header value to set.
|
|
|
|
* http_method HTTP method to use for the download.
|
|
|
|
* http_headers A dictionary of additional HTTP headers
|
|
|
|
to add to the request.
|
|
|
|
* http_post_data Additional data to send with a POST
|
|
|
|
request.
|
2013-12-16 04:09:30 +01:00
|
|
|
url: Final video URL.
|
2013-06-23 19:57:38 +02:00
|
|
|
ext: Video filename extension.
|
2013-12-16 14:13:40 +01:00
|
|
|
format: The video format, defaults to ext (used for --get-format)
|
|
|
|
player_url: SWF Player URL (used for rtmpdump).
|
2013-10-04 11:09:43 +02:00
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
The following fields are optional:
|
|
|
|
|
2014-03-03 12:06:28 +01:00
|
|
|
display_id An alternative identifier for the video, not necessarily
|
|
|
|
unique, but available before title. Typically, id is
|
|
|
|
something like "4234987", title "Dancing naked mole rats",
|
|
|
|
and display_id "dancing-naked-mole-rats"
|
2014-06-07 15:33:45 +02:00
|
|
|
thumbnails: A list of dictionaries, with the following entries:
|
|
|
|
* "url"
|
|
|
|
* "width" (optional, int)
|
|
|
|
* "height" (optional, int)
|
|
|
|
* "resolution" (optional, string "{width}x{height"},
|
|
|
|
deprecated)
|
2013-06-23 19:57:38 +02:00
|
|
|
thumbnail: Full URL to a video thumbnail image.
|
|
|
|
description: One-line video description.
|
|
|
|
uploader: Full name of the video uploader.
|
2014-03-13 18:21:55 +01:00
|
|
|
timestamp: UNIX timestamp of the moment the video became available.
|
2013-06-23 19:57:38 +02:00
|
|
|
upload_date: Video upload date (YYYYMMDD).
|
2014-03-13 18:21:55 +01:00
|
|
|
If not explicitly set, calculated from timestamp.
|
2013-06-23 19:57:38 +02:00
|
|
|
uploader_id: Nickname or id of the video uploader.
|
|
|
|
location: Physical location of the video.
|
2013-06-26 11:03:44 +02:00
|
|
|
subtitles: The subtitle file contents as a dictionary in the format
|
|
|
|
{language: subtitles}.
|
2013-12-16 04:09:30 +01:00
|
|
|
duration: Length of the video in seconds, as an integer.
|
2013-06-29 16:32:28 +02:00
|
|
|
view_count: How many users have watched the video on the platform.
|
2013-12-05 18:29:07 +01:00
|
|
|
like_count: Number of positive ratings of the video
|
|
|
|
dislike_count: Number of negative ratings of the video
|
|
|
|
comment_count: Number of comments on the video
|
2013-10-06 06:06:30 +02:00
|
|
|
age_limit: Age restriction for the video, as an integer (years)
|
2013-11-03 12:11:13 +01:00
|
|
|
webpage_url: The url to the video webpage, if given to youtube-dl it
|
|
|
|
should allow to get the same result again. (It will be set
|
|
|
|
by YoutubeDL if it's missing)
|
2014-05-15 12:41:42 +02:00
|
|
|
categories: A list of categories that the video falls in, for example
|
|
|
|
["Sports", "Berlin"]
|
2013-06-23 19:57:38 +02:00
|
|
|
|
2013-10-04 10:40:42 +02:00
|
|
|
Unless mentioned otherwise, the fields should be Unicode strings.
|
2013-06-23 19:57:38 +02:00
|
|
|
|
|
|
|
Subclasses of this one should re-define the _real_initialize() and
|
|
|
|
_real_extract() methods and define a _VALID_URL regexp.
|
|
|
|
Probably, they should also be added to the list of extractors.
|
|
|
|
|
|
|
|
Finally, the _WORKING attribute should be set to False for broken IEs
|
|
|
|
in order to warn the users and skip the tests.
|
|
|
|
"""
|
|
|
|
|
|
|
|
_ready = False
|
|
|
|
_downloader = None
|
|
|
|
_WORKING = True
|
|
|
|
|
|
|
|
def __init__(self, downloader=None):
|
|
|
|
"""Constructor. Receives an optional downloader."""
|
|
|
|
self._ready = False
|
|
|
|
self.set_downloader(downloader)
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def suitable(cls, url):
|
|
|
|
"""Receives a URL and returns True if suitable for this IE."""
|
2013-08-21 04:06:46 +02:00
|
|
|
|
|
|
|
# This does not use has/getattr intentionally - we want to know whether
|
|
|
|
# we have cached the regexp for *this* class, whereas getattr would also
|
|
|
|
# match the superclass
|
|
|
|
if '_VALID_URL_RE' not in cls.__dict__:
|
|
|
|
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
|
|
|
|
return cls._VALID_URL_RE.match(url) is not None
|
2013-06-23 19:57:38 +02:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def working(cls):
|
|
|
|
"""Getter method for _WORKING."""
|
|
|
|
return cls._WORKING
|
|
|
|
|
|
|
|
def initialize(self):
|
|
|
|
"""Initializes an instance (authentication, etc)."""
|
|
|
|
if not self._ready:
|
|
|
|
self._real_initialize()
|
|
|
|
self._ready = True
|
|
|
|
|
|
|
|
def extract(self, url):
|
|
|
|
"""Extracts URL information and returns it in list of dicts."""
|
|
|
|
self.initialize()
|
|
|
|
return self._real_extract(url)
|
|
|
|
|
|
|
|
def set_downloader(self, downloader):
|
|
|
|
"""Sets the downloader for this IE."""
|
|
|
|
self._downloader = downloader
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
"""Real initialization process. Redefine in subclasses."""
|
|
|
|
pass
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
"""Real extraction process. Redefine in subclasses."""
|
|
|
|
pass
|
|
|
|
|
2013-07-08 15:14:27 +02:00
|
|
|
@classmethod
|
|
|
|
def ie_key(cls):
|
|
|
|
"""A string for getting the InfoExtractor with get_info_extractor"""
|
|
|
|
return cls.__name__[:-2]
|
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
@property
|
|
|
|
def IE_NAME(self):
|
|
|
|
return type(self).__name__[:-2]
|
|
|
|
|
2013-12-09 01:49:01 +01:00
|
|
|
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
|
2013-06-23 19:57:38 +02:00
|
|
|
""" Returns the response handle """
|
|
|
|
if note is None:
|
|
|
|
self.report_download_webpage(video_id)
|
|
|
|
elif note is not False:
|
2013-12-09 01:49:01 +01:00
|
|
|
if video_id is None:
|
|
|
|
self.to_screen(u'%s' % (note,))
|
|
|
|
else:
|
|
|
|
self.to_screen(u'%s: %s' % (video_id, note))
|
2013-06-23 19:57:38 +02:00
|
|
|
try:
|
2013-11-22 19:57:52 +01:00
|
|
|
return self._downloader.urlopen(url_or_request)
|
2013-06-23 19:57:38 +02:00
|
|
|
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
2013-12-20 17:05:28 +01:00
|
|
|
if errnote is False:
|
|
|
|
return False
|
2013-06-23 19:57:38 +02:00
|
|
|
if errnote is None:
|
|
|
|
errnote = u'Unable to download webpage'
|
2013-12-09 01:49:01 +01:00
|
|
|
errmsg = u'%s: %s' % (errnote, compat_str(err))
|
|
|
|
if fatal:
|
|
|
|
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
|
|
|
|
else:
|
|
|
|
self._downloader.report_warning(errmsg)
|
|
|
|
return False
|
2013-06-23 19:57:38 +02:00
|
|
|
|
2013-12-09 01:49:01 +01:00
|
|
|
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
|
2013-06-23 19:57:38 +02:00
|
|
|
""" Returns a tuple (page content as string, URL handle) """
|
2013-07-13 22:52:12 +02:00
|
|
|
|
|
|
|
# Strip hashes from the URL (#1038)
|
|
|
|
if isinstance(url_or_request, (compat_str, str)):
|
|
|
|
url_or_request = url_or_request.partition('#')[0]
|
|
|
|
|
2013-12-09 01:49:01 +01:00
|
|
|
urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
|
|
|
|
if urlh is False:
|
|
|
|
assert not fatal
|
|
|
|
return False
|
2013-06-23 19:57:38 +02:00
|
|
|
content_type = urlh.headers.get('Content-Type', '')
|
2013-08-28 13:59:08 +02:00
|
|
|
webpage_bytes = urlh.read()
|
2013-06-23 19:57:38 +02:00
|
|
|
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
|
|
|
|
if m:
|
|
|
|
encoding = m.group(1)
|
|
|
|
else:
|
2013-08-29 11:35:15 +02:00
|
|
|
m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
|
2013-08-28 13:59:08 +02:00
|
|
|
webpage_bytes[:1024])
|
|
|
|
if m:
|
|
|
|
encoding = m.group(1).decode('ascii')
|
2014-01-21 01:39:39 +01:00
|
|
|
elif webpage_bytes.startswith(b'\xff\xfe'):
|
|
|
|
encoding = 'utf-16'
|
2013-08-28 13:59:08 +02:00
|
|
|
else:
|
|
|
|
encoding = 'utf-8'
|
2013-06-23 19:57:38 +02:00
|
|
|
if self._downloader.params.get('dump_intermediate_pages', False):
|
|
|
|
try:
|
|
|
|
url = url_or_request.get_full_url()
|
|
|
|
except AttributeError:
|
|
|
|
url = url_or_request
|
|
|
|
self.to_screen(u'Dumping request to ' + url)
|
|
|
|
dump = base64.b64encode(webpage_bytes).decode('ascii')
|
|
|
|
self._downloader.to_screen(dump)
|
2013-10-28 10:44:02 +01:00
|
|
|
if self._downloader.params.get('write_pages', False):
|
|
|
|
try:
|
|
|
|
url = url_or_request.get_full_url()
|
|
|
|
except AttributeError:
|
|
|
|
url = url_or_request
|
2014-05-15 12:39:33 +02:00
|
|
|
basen = '%s_%s' % (video_id, url)
|
2014-05-12 21:56:10 +02:00
|
|
|
if len(basen) > 240:
|
|
|
|
h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
|
|
|
|
basen = basen[:240 - len(h)] + h
|
|
|
|
raw_filename = basen + '.dump'
|
2013-10-28 10:44:02 +01:00
|
|
|
filename = sanitize_filename(raw_filename, restricted=True)
|
|
|
|
self.to_screen(u'Saving request to ' + filename)
|
|
|
|
with open(filename, 'wb') as outf:
|
|
|
|
outf.write(webpage_bytes)
|
|
|
|
|
2014-04-07 23:09:53 +02:00
|
|
|
try:
|
|
|
|
content = webpage_bytes.decode(encoding, 'replace')
|
|
|
|
except LookupError:
|
|
|
|
content = webpage_bytes.decode('utf-8', 'replace')
|
2014-04-03 06:07:35 +02:00
|
|
|
|
|
|
|
if (u'<title>Access to this site is blocked</title>' in content and
|
|
|
|
u'Websense' in content[:512]):
|
2014-04-03 08:12:53 +02:00
|
|
|
msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
|
2014-04-03 06:07:35 +02:00
|
|
|
blocked_iframe = self._html_search_regex(
|
|
|
|
r'<iframe src="([^"]+)"', content,
|
|
|
|
u'Websense information URL', default=None)
|
|
|
|
if blocked_iframe:
|
|
|
|
msg += u' Visit %s for more details' % blocked_iframe
|
|
|
|
raise ExtractorError(msg, expected=True)
|
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
return (content, urlh)
|
|
|
|
|
2013-12-09 01:49:01 +01:00
|
|
|
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
|
2013-06-23 19:57:38 +02:00
|
|
|
""" Returns the data of the page as a string """
|
2013-12-09 01:49:01 +01:00
|
|
|
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
|
|
|
|
if res is False:
|
|
|
|
return res
|
|
|
|
else:
|
|
|
|
content, _ = res
|
|
|
|
return content
|
2013-06-23 19:57:38 +02:00
|
|
|
|
2013-11-28 05:47:50 +01:00
|
|
|
def _download_xml(self, url_or_request, video_id,
|
2013-12-10 12:45:22 +01:00
|
|
|
note=u'Downloading XML', errnote=u'Unable to download XML',
|
2014-04-21 13:45:27 +02:00
|
|
|
transform_source=None, fatal=True):
|
2013-11-24 14:59:19 +01:00
|
|
|
"""Return the xml as an xml.etree.ElementTree.Element"""
|
2014-04-21 13:45:27 +02:00
|
|
|
xml_string = self._download_webpage(
|
|
|
|
url_or_request, video_id, note, errnote, fatal=fatal)
|
|
|
|
if xml_string is False:
|
|
|
|
return xml_string
|
2013-12-10 12:45:22 +01:00
|
|
|
if transform_source:
|
|
|
|
xml_string = transform_source(xml_string)
|
2013-11-24 14:59:19 +01:00
|
|
|
return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
|
|
|
|
|
2014-01-07 09:35:34 +01:00
|
|
|
def _download_json(self, url_or_request, video_id,
|
|
|
|
note=u'Downloading JSON metadata',
|
2014-02-09 17:56:10 +01:00
|
|
|
errnote=u'Unable to download JSON metadata',
|
2014-07-23 01:27:25 +02:00
|
|
|
transform_source=None,
|
|
|
|
fatal=True):
|
|
|
|
json_string = self._download_webpage(
|
|
|
|
url_or_request, video_id, note, errnote, fatal=fatal)
|
|
|
|
if (not fatal) and json_string is False:
|
|
|
|
return None
|
2014-02-09 17:56:10 +01:00
|
|
|
if transform_source:
|
|
|
|
json_string = transform_source(json_string)
|
2014-01-07 09:35:34 +01:00
|
|
|
try:
|
|
|
|
return json.loads(json_string)
|
|
|
|
except ValueError as ve:
|
|
|
|
raise ExtractorError('Failed to download JSON', cause=ve)
|
|
|
|
|
2013-12-23 15:57:43 +01:00
|
|
|
def report_warning(self, msg, video_id=None):
|
|
|
|
idstr = u'' if video_id is None else u'%s: ' % video_id
|
|
|
|
self._downloader.report_warning(
|
|
|
|
u'[%s] %s%s' % (self.IE_NAME, idstr, msg))
|
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
def to_screen(self, msg):
|
|
|
|
"""Print msg to screen, prefixing it with '[ie_name]'"""
|
|
|
|
self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
|
|
|
|
|
|
|
|
def report_extraction(self, id_or_name):
|
|
|
|
"""Report information extraction."""
|
|
|
|
self.to_screen(u'%s: Extracting information' % id_or_name)
|
|
|
|
|
|
|
|
def report_download_webpage(self, video_id):
|
|
|
|
"""Report webpage download."""
|
|
|
|
self.to_screen(u'%s: Downloading webpage' % video_id)
|
|
|
|
|
|
|
|
def report_age_confirmation(self):
|
|
|
|
"""Report attempt to confirm age."""
|
|
|
|
self.to_screen(u'Confirming age')
|
|
|
|
|
2013-07-07 23:24:34 +02:00
|
|
|
def report_login(self):
|
|
|
|
"""Report attempt to log in."""
|
|
|
|
self.to_screen(u'Logging in')
|
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
#Methods for following #608
|
2013-12-19 20:28:52 +01:00
|
|
|
@staticmethod
|
|
|
|
def url_result(url, ie=None, video_id=None):
|
2013-06-23 19:57:38 +02:00
|
|
|
"""Returns a url that points to a page that should be processed"""
|
|
|
|
#TODO: ie should be the class used for getting the info
|
|
|
|
video_info = {'_type': 'url',
|
|
|
|
'url': url,
|
|
|
|
'ie_key': ie}
|
2013-11-22 22:46:46 +01:00
|
|
|
if video_id is not None:
|
|
|
|
video_info['id'] = video_id
|
2013-06-23 19:57:38 +02:00
|
|
|
return video_info
|
2013-12-19 20:28:52 +01:00
|
|
|
@staticmethod
|
|
|
|
def playlist_result(entries, playlist_id=None, playlist_title=None):
|
2013-06-23 19:57:38 +02:00
|
|
|
"""Returns a playlist"""
|
|
|
|
video_info = {'_type': 'playlist',
|
|
|
|
'entries': entries}
|
|
|
|
if playlist_id:
|
|
|
|
video_info['id'] = playlist_id
|
|
|
|
if playlist_title:
|
|
|
|
video_info['title'] = playlist_title
|
|
|
|
return video_info
|
|
|
|
|
2013-12-17 02:49:54 +01:00
|
|
|
def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
|
2013-06-23 19:57:38 +02:00
|
|
|
"""
|
|
|
|
Perform a regex search on the given string, using a single or a list of
|
|
|
|
patterns returning the first matching group.
|
|
|
|
In case of failure return a default value or raise a WARNING or a
|
2013-10-23 14:38:03 +02:00
|
|
|
RegexNotFoundError, depending on fatal, specifying the field name.
|
2013-06-23 19:57:38 +02:00
|
|
|
"""
|
|
|
|
if isinstance(pattern, (str, compat_str, compiled_regex_type)):
|
|
|
|
mobj = re.search(pattern, string, flags)
|
|
|
|
else:
|
|
|
|
for p in pattern:
|
|
|
|
mobj = re.search(p, string, flags)
|
2014-07-25 10:43:03 +02:00
|
|
|
if mobj:
|
|
|
|
break
|
2013-06-23 19:57:38 +02:00
|
|
|
|
2013-12-14 16:40:51 +01:00
|
|
|
if os.name != 'nt' and sys.stderr.isatty():
|
2013-06-23 19:57:38 +02:00
|
|
|
_name = u'\033[0;34m%s\033[0m' % name
|
|
|
|
else:
|
|
|
|
_name = name
|
|
|
|
|
|
|
|
if mobj:
|
|
|
|
# return the first matching group
|
|
|
|
return next(g for g in mobj.groups() if g is not None)
|
2013-12-17 02:49:54 +01:00
|
|
|
elif default is not _NO_DEFAULT:
|
2013-06-23 19:57:38 +02:00
|
|
|
return default
|
|
|
|
elif fatal:
|
2013-10-23 14:38:03 +02:00
|
|
|
raise RegexNotFoundError(u'Unable to extract %s' % _name)
|
2013-06-23 19:57:38 +02:00
|
|
|
else:
|
|
|
|
self._downloader.report_warning(u'unable to extract %s; '
|
2013-06-25 16:43:29 +02:00
|
|
|
u'please report this issue on http://yt-dl.org/bug' % _name)
|
2013-06-23 19:57:38 +02:00
|
|
|
return None
|
|
|
|
|
2013-12-17 02:49:54 +01:00
|
|
|
def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
|
2013-06-23 19:57:38 +02:00
|
|
|
"""
|
|
|
|
Like _search_regex, but strips HTML tags and unescapes entities.
|
|
|
|
"""
|
|
|
|
res = self._search_regex(pattern, string, name, default, fatal, flags)
|
|
|
|
if res:
|
|
|
|
return clean_html(res).strip()
|
|
|
|
else:
|
|
|
|
return res
|
|
|
|
|
2013-07-07 23:24:34 +02:00
|
|
|
def _get_login_info(self):
|
|
|
|
"""
|
|
|
|
Get the the login info as (username, password)
|
|
|
|
It will look in the netrc file using the _NETRC_MACHINE value
|
|
|
|
If there's no info available, return (None, None)
|
|
|
|
"""
|
|
|
|
if self._downloader is None:
|
|
|
|
return (None, None)
|
|
|
|
|
|
|
|
username = None
|
|
|
|
password = None
|
|
|
|
downloader_params = self._downloader.params
|
|
|
|
|
|
|
|
# Attempt to use provided username and password or .netrc data
|
|
|
|
if downloader_params.get('username', None) is not None:
|
|
|
|
username = downloader_params['username']
|
|
|
|
password = downloader_params['password']
|
|
|
|
elif downloader_params.get('usenetrc', False):
|
|
|
|
try:
|
|
|
|
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
|
|
|
|
if info is not None:
|
|
|
|
username = info[0]
|
|
|
|
password = info[2]
|
|
|
|
else:
|
|
|
|
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
|
|
|
|
except (IOError, netrc.NetrcParseError) as err:
|
|
|
|
self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
|
|
|
|
|
|
|
|
return (username, password)
|
|
|
|
|
2014-08-16 23:28:41 +02:00
|
|
|
def _get_tfa_info(self):
|
|
|
|
"""
|
|
|
|
Get the two-factor authentication info
|
|
|
|
TODO - asking the user will be required for sms/phone verify
|
|
|
|
currently just uses the command line option
|
|
|
|
If there's no info available, return None
|
|
|
|
"""
|
|
|
|
if self._downloader is None:
|
|
|
|
return None
|
|
|
|
downloader_params = self._downloader.params
|
|
|
|
|
|
|
|
if downloader_params.get('twofactor', None) is not None:
|
|
|
|
return downloader_params['twofactor']
|
|
|
|
|
|
|
|
return None
|
|
|
|
|
2013-07-12 19:00:19 +02:00
|
|
|
# Helper functions for extracting OpenGraph info
|
|
|
|
@staticmethod
|
2013-11-15 12:24:54 +01:00
|
|
|
def _og_regexes(prop):
|
2014-01-30 21:57:33 +01:00
|
|
|
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
|
2014-01-03 12:51:37 +01:00
|
|
|
property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
|
2013-11-15 12:54:13 +01:00
|
|
|
template = r'<meta[^>]+?%s[^>]+?%s'
|
2013-11-15 12:24:54 +01:00
|
|
|
return [
|
2013-11-15 12:54:13 +01:00
|
|
|
template % (property_re, content_re),
|
|
|
|
template % (content_re, property_re),
|
2013-11-15 12:24:54 +01:00
|
|
|
]
|
2013-07-12 19:00:19 +02:00
|
|
|
|
2013-07-13 20:39:47 +02:00
|
|
|
def _og_search_property(self, prop, html, name=None, **kargs):
|
2013-07-12 19:00:19 +02:00
|
|
|
if name is None:
|
2013-07-13 20:39:47 +02:00
|
|
|
name = 'OpenGraph %s' % prop
|
2013-11-15 12:24:54 +01:00
|
|
|
escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
|
2013-11-12 10:36:23 +01:00
|
|
|
if escaped is None:
|
|
|
|
return None
|
|
|
|
return unescapeHTML(escaped)
|
2013-07-12 19:00:19 +02:00
|
|
|
|
|
|
|
def _og_search_thumbnail(self, html, **kargs):
|
2013-07-13 20:39:47 +02:00
|
|
|
return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
|
2013-07-12 19:00:19 +02:00
|
|
|
|
|
|
|
def _og_search_description(self, html, **kargs):
|
|
|
|
return self._og_search_property('description', html, fatal=False, **kargs)
|
|
|
|
|
|
|
|
def _og_search_title(self, html, **kargs):
|
|
|
|
return self._og_search_property('title', html, **kargs)
|
|
|
|
|
2013-10-28 07:34:29 +01:00
|
|
|
def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
|
2014-08-21 13:05:24 +02:00
|
|
|
regexes = self._og_regexes('video') + self._og_regexes('video:url')
|
|
|
|
if secure:
|
|
|
|
regexes = self._og_regexes('video:secure_url') + regexes
|
2013-10-28 07:34:29 +01:00
|
|
|
return self._html_search_regex(regexes, html, name, **kargs)
|
2013-07-12 19:00:19 +02:00
|
|
|
|
2014-06-26 16:34:36 +02:00
|
|
|
def _og_search_url(self, html, **kargs):
|
|
|
|
return self._og_search_property('url', html, **kargs)
|
|
|
|
|
2014-07-11 15:38:18 +02:00
|
|
|
def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
|
2013-11-20 06:13:19 +01:00
|
|
|
if display_name is None:
|
|
|
|
display_name = name
|
|
|
|
return self._html_search_regex(
|
2013-12-02 17:08:17 +01:00
|
|
|
r'''(?ix)<meta
|
2014-07-21 12:47:01 +02:00
|
|
|
(?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?)
|
2013-11-20 06:13:19 +01:00
|
|
|
[^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
|
2014-07-11 15:38:18 +02:00
|
|
|
html, display_name, fatal=fatal, **kwargs)
|
2013-11-20 06:13:19 +01:00
|
|
|
|
|
|
|
def _dc_search_uploader(self, html):
|
|
|
|
return self._html_search_meta('dc.creator', html, 'uploader')
|
|
|
|
|
2013-10-06 06:06:30 +02:00
|
|
|
def _rta_search(self, html):
|
|
|
|
# See http://www.rtalabel.org/index.php?content=howtofaq#single
|
|
|
|
if re.search(r'(?ix)<meta\s+name="rating"\s+'
|
|
|
|
r' content="RTA-5042-1996-1400-1577-RTA"',
|
|
|
|
html):
|
|
|
|
return 18
|
|
|
|
return 0
|
|
|
|
|
2013-11-20 06:13:19 +01:00
|
|
|
def _media_rating_search(self, html):
|
|
|
|
# See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/
|
|
|
|
rating = self._html_search_meta('rating', html)
|
|
|
|
|
|
|
|
if not rating:
|
|
|
|
return None
|
|
|
|
|
|
|
|
RATING_TABLE = {
|
|
|
|
'safe for kids': 0,
|
|
|
|
'general': 8,
|
|
|
|
'14 years': 14,
|
|
|
|
'mature': 17,
|
|
|
|
'restricted': 19,
|
|
|
|
}
|
|
|
|
return RATING_TABLE.get(rating.lower(), None)
|
|
|
|
|
2014-01-29 18:03:32 +01:00
|
|
|
def _twitter_search_player(self, html):
|
|
|
|
return self._html_search_meta('twitter:player', html,
|
|
|
|
'twitter card player')
|
|
|
|
|
2013-12-24 12:25:22 +01:00
|
|
|
def _sort_formats(self, formats):
|
2014-01-27 07:31:54 +01:00
|
|
|
if not formats:
|
|
|
|
raise ExtractorError(u'No video formats found')
|
|
|
|
|
2013-12-24 12:25:22 +01:00
|
|
|
def _formats_key(f):
|
2013-12-24 12:40:23 +01:00
|
|
|
# TODO remove the following workaround
|
|
|
|
from ..utils import determine_ext
|
|
|
|
if not f.get('ext') and 'url' in f:
|
|
|
|
f['ext'] = determine_ext(f['url'])
|
|
|
|
|
2013-12-24 12:25:22 +01:00
|
|
|
preference = f.get('preference')
|
|
|
|
if preference is None:
|
2013-12-24 23:32:04 +01:00
|
|
|
proto = f.get('protocol')
|
|
|
|
if proto is None:
|
|
|
|
proto = compat_urllib_parse_urlparse(f.get('url', '')).scheme
|
|
|
|
|
|
|
|
preference = 0 if proto in ['http', 'https'] else -0.1
|
2013-12-24 12:25:22 +01:00
|
|
|
if f.get('ext') in ['f4f', 'f4m']: # Not yet supported
|
|
|
|
preference -= 0.5
|
|
|
|
|
|
|
|
if f.get('vcodec') == 'none': # audio only
|
|
|
|
if self._downloader.params.get('prefer_free_formats'):
|
|
|
|
ORDER = [u'aac', u'mp3', u'm4a', u'webm', u'ogg', u'opus']
|
|
|
|
else:
|
|
|
|
ORDER = [u'webm', u'opus', u'ogg', u'mp3', u'aac', u'm4a']
|
|
|
|
ext_preference = 0
|
|
|
|
try:
|
|
|
|
audio_ext_preference = ORDER.index(f['ext'])
|
|
|
|
except ValueError:
|
|
|
|
audio_ext_preference = -1
|
|
|
|
else:
|
|
|
|
if self._downloader.params.get('prefer_free_formats'):
|
|
|
|
ORDER = [u'flv', u'mp4', u'webm']
|
|
|
|
else:
|
|
|
|
ORDER = [u'webm', u'flv', u'mp4']
|
|
|
|
try:
|
|
|
|
ext_preference = ORDER.index(f['ext'])
|
|
|
|
except ValueError:
|
|
|
|
ext_preference = -1
|
|
|
|
audio_ext_preference = 0
|
|
|
|
|
|
|
|
return (
|
|
|
|
preference,
|
2014-01-06 17:15:27 +01:00
|
|
|
f.get('quality') if f.get('quality') is not None else -1,
|
2013-12-24 12:25:22 +01:00
|
|
|
f.get('height') if f.get('height') is not None else -1,
|
|
|
|
f.get('width') if f.get('width') is not None else -1,
|
|
|
|
ext_preference,
|
2014-01-07 10:25:34 +01:00
|
|
|
f.get('tbr') if f.get('tbr') is not None else -1,
|
2013-12-24 12:25:22 +01:00
|
|
|
f.get('vbr') if f.get('vbr') is not None else -1,
|
|
|
|
f.get('abr') if f.get('abr') is not None else -1,
|
|
|
|
audio_ext_preference,
|
|
|
|
f.get('filesize') if f.get('filesize') is not None else -1,
|
2014-07-21 12:02:44 +02:00
|
|
|
f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
|
2013-12-24 12:25:22 +01:00
|
|
|
f.get('format_id'),
|
|
|
|
)
|
|
|
|
formats.sort(key=_formats_key)
|
2013-11-20 06:13:19 +01:00
|
|
|
|
2014-05-05 03:12:41 +02:00
|
|
|
def http_scheme(self):
|
|
|
|
""" Either "https:" or "https:", depending on the user's preferences """
|
|
|
|
return (
|
|
|
|
'http:'
|
|
|
|
if self._downloader.params.get('prefer_insecure', False)
|
|
|
|
else 'https:')
|
|
|
|
|
2014-05-13 09:42:38 +02:00
|
|
|
def _proto_relative_url(self, url, scheme=None):
|
|
|
|
if url is None:
|
|
|
|
return url
|
|
|
|
if url.startswith('//'):
|
|
|
|
if scheme is None:
|
|
|
|
scheme = self.http_scheme()
|
|
|
|
return scheme + url
|
|
|
|
else:
|
|
|
|
return url
|
|
|
|
|
2014-07-11 10:57:08 +02:00
|
|
|
def _sleep(self, timeout, video_id, msg_template=None):
|
|
|
|
if msg_template is None:
|
|
|
|
msg_template = u'%(video_id)s: Waiting for %(timeout)s seconds'
|
|
|
|
msg = msg_template % {'video_id': video_id, 'timeout': timeout}
|
|
|
|
self.to_screen(msg)
|
|
|
|
time.sleep(timeout)
|
|
|
|
|
2014-07-28 15:25:56 +02:00
|
|
|
def _extract_f4m_formats(self, manifest_url, video_id):
|
2014-07-28 15:42:19 +02:00
|
|
|
manifest = self._download_xml(
|
|
|
|
manifest_url, video_id, 'Downloading f4m manifest',
|
|
|
|
'Unable to download f4m manifest')
|
2014-07-28 15:25:56 +02:00
|
|
|
|
|
|
|
formats = []
|
|
|
|
for media_el in manifest.findall('{http://ns.adobe.com/f4m/1.0}media'):
|
|
|
|
formats.append({
|
|
|
|
'url': manifest_url,
|
|
|
|
'ext': 'flv',
|
|
|
|
'tbr': int_or_none(media_el.attrib.get('bitrate')),
|
|
|
|
'width': int_or_none(media_el.attrib.get('width')),
|
|
|
|
'height': int_or_none(media_el.attrib.get('height')),
|
|
|
|
})
|
|
|
|
self._sort_formats(formats)
|
|
|
|
|
|
|
|
return formats
|
|
|
|
|
2013-10-06 06:06:30 +02:00
|
|
|
|
2013-06-23 19:57:38 +02:00
|
|
|
class SearchInfoExtractor(InfoExtractor):
|
|
|
|
"""
|
|
|
|
Base class for paged search queries extractors.
|
|
|
|
They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
|
|
|
|
Instances should define _SEARCH_KEY and _MAX_RESULTS.
|
|
|
|
"""
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def _make_valid_url(cls):
|
|
|
|
return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def suitable(cls, url):
|
|
|
|
return re.match(cls._make_valid_url(), url) is not None
|
|
|
|
|
|
|
|
def _real_extract(self, query):
|
|
|
|
mobj = re.match(self._make_valid_url(), query)
|
|
|
|
if mobj is None:
|
|
|
|
raise ExtractorError(u'Invalid search query "%s"' % query)
|
|
|
|
|
|
|
|
prefix = mobj.group('prefix')
|
|
|
|
query = mobj.group('query')
|
|
|
|
if prefix == '':
|
|
|
|
return self._get_n_results(query, 1)
|
|
|
|
elif prefix == 'all':
|
|
|
|
return self._get_n_results(query, self._MAX_RESULTS)
|
|
|
|
else:
|
|
|
|
n = int(prefix)
|
|
|
|
if n <= 0:
|
|
|
|
raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
|
|
|
|
elif n > self._MAX_RESULTS:
|
|
|
|
self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
|
|
|
|
n = self._MAX_RESULTS
|
|
|
|
return self._get_n_results(query, n)
|
|
|
|
|
|
|
|
def _get_n_results(self, query, n):
|
|
|
|
"""Get a specified number of results for a query"""
|
2013-10-18 00:49:45 +02:00
|
|
|
raise NotImplementedError("This method must be implemented by subclasses")
|
2013-07-01 18:52:19 +02:00
|
|
|
|
|
|
|
@property
|
|
|
|
def SEARCH_KEY(self):
|
|
|
|
return self._SEARCH_KEY
|