mirror
/
yt-dlc
mirror of https://github.com/blackjack4494/yt-dlc.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Updated to release 2020.11.21.1

pull/245/head
pukkandan 2020-11-21 20:20:42 +05:30
parent 3462ffa892
commit a0566bbf5c
29 changed files with 559 additions and 360 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/parameters.json
View File

@ -37,7 +37,7 @@
"writeinfojson": true,
"writesubtitles": false,
"allsubtitles": false,
"listssubtitles": false,
"listsubtitles": false,
"socket_timeout": 20,
"fixup": "never"
}

70
test/test_YoutubeDL.py
View File

@ -919,6 +919,76 @@ class TestYoutubeDL(unittest.TestCase):
self.assertEqual(downloaded['extractor'], 'testex')
self.assertEqual(downloaded['extractor_key'], 'TestEx')
# Test case for https://github.com/ytdl-org/youtube-dl/issues/27064
def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self):
class _YDL(YDL):
def __init__(self, *args, **kwargs):
super(_YDL, self).__init__(*args, **kwargs)
def trouble(self, s, tb=None):
pass
ydl = _YDL({
'format': 'extra',
'ignoreerrors': True,
})
class VideoIE(InfoExtractor):
_VALID_URL = r'video:(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
formats = [{
'format_id': 'default',
'url': 'url:',
}]
if video_id == '0':
raise ExtractorError('foo')
if video_id == '2':
formats.append({
'format_id': 'extra',
'url': TEST_URL,
})
return {
'id': video_id,
'title': 'Video %s' % video_id,
'formats': formats,
}
class PlaylistIE(InfoExtractor):
_VALID_URL = r'playlist:'
def _entries(self):
for n in range(3):
video_id = compat_str(n)
yield {
'_type': 'url_transparent',
'ie_key': VideoIE.ie_key(),
'id': video_id,
'url': 'video:%s' % video_id,
'title': 'Video Transparent %s' % video_id,
}
def _real_extract(self, url):
return self.playlist_result(self._entries())
ydl.add_info_extractor(VideoIE(ydl))
ydl.add_info_extractor(PlaylistIE(ydl))
info = ydl.extract_info('playlist:')
entries = info['entries']
self.assertEqual(len(entries), 3)
self.assertTrue(entries[0] is None)
self.assertTrue(entries[1] is None)
self.assertEqual(len(ydl.downloaded_info_dicts), 1)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(entries[2], downloaded)
self.assertEqual(downloaded['url'], TEST_URL)
self.assertEqual(downloaded['title'], 'Video Transparent 2')
self.assertEqual(downloaded['id'], '2')
self.assertEqual(downloaded['extractor'], 'Video')
self.assertEqual(downloaded['extractor_key'], 'Video')
if __name__ == '__main__':
unittest.main()

79
youtube_dlc/YoutubeDL.py
View File

@ -830,34 +830,23 @@ class YoutubeDL(object):
'and will probably not work.')
try:
try:
temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url)
except (AssertionError, IndexError, AttributeError):
temp_id = None
if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
self.to_screen("[%s] %s: has already been recorded in archive" % (
ie_key, temp_id))
break
temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url)
except (AssertionError, IndexError, AttributeError):
temp_id = None
if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
self.to_screen("[%s] %s: has already been recorded in archive" % (
ie_key, temp_id))
break
ie_result = ie.extract(url)
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
break
if isinstance(ie_result, list):
# Backwards compatibility: old IE result format
ie_result = {
'_type': 'compat_list',
'entries': ie_result,
}
if info_dict:
if info_dict.get('id'):
ie_result['id'] = info_dict['id']
if info_dict.get('title'):
ie_result['title'] = info_dict['title']
self.add_default_extra_info(ie_result, ie, url)
if process:
return self.process_ie_result(ie_result, download, extra_info)
else:
return ie_result
return self.__extract_info(url, ie, download, extra_info, process, info_dict)
else:
self.report_error('no suitable InfoExtractor for URL %s' % url)
def __handle_extraction_exceptions(func):
def wrapper(self, *args, **kwargs):
try:
return func(self, *args, **kwargs)
except GeoRestrictedError as e:
msg = e.msg
if e.countries:
@ -865,20 +854,38 @@ class YoutubeDL(object):
map(ISO3166Utils.short2full, e.countries))
msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.'
self.report_error(msg)
break
except ExtractorError as e: # An error we somewhat expected
self.report_error(compat_str(e), e.format_traceback())
break
except MaxDownloadsReached:
raise
except Exception as e:
if self.params.get('ignoreerrors', False):
self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc()))
break
else:
raise
return wrapper
@__handle_extraction_exceptions
def __extract_info(self, url, ie, download, extra_info, process, info_dict):
ie_result = ie.extract(url)
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
return
if isinstance(ie_result, list):
# Backwards compatibility: old IE result format
ie_result = {
'_type': 'compat_list',
'entries': ie_result,
}
if info_dict:
if info_dict.get('id'):
ie_result['id'] = info_dict['id']
if info_dict.get('title'):
ie_result['title'] = info_dict['title']
self.add_default_extra_info(ie_result, ie, url)
if process:
return self.process_ie_result(ie_result, download, extra_info)
else:
self.report_error('no suitable InfoExtractor for URL %s' % url)
return ie_result
def add_default_extra_info(self, ie_result, ie, url):
self.add_extra_info(ie_result, {
@ -1057,9 +1064,8 @@ class YoutubeDL(object):
self.to_screen('[download] ' + reason)
continue
entry_result = self.process_ie_result(entry,
download=download,
extra_info=extra)
entry_result = self.__process_iterable_entry(entry, download, extra)
# TODO: skip failed (empty) entries?
playlist_results.append(entry_result)
ie_result['entries'] = playlist_results
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
@ -1088,6 +1094,11 @@ class YoutubeDL(object):
else:
raise Exception('Invalid result type: %s' % result_type)
@__handle_extraction_exceptions
def __process_iterable_entry(self, entry, download, extra_info):
return self.process_ie_result(
entry, download=download, extra_info=extra_info)
def _build_format_filter(self, filter_spec):
" Returns a function to filter the formats according to the filter_spec "

2
youtube_dlc/compat.py
View File

@ -2345,7 +2345,7 @@ except ImportError: # Python <3.4
# HTMLParseError has been deprecated in Python 3.3 and removed in
# Python 3.5. Introducing dummy exception for Python >3.5 for compatible
# and uniform cross-version exceptiong handling
# and uniform cross-version exception handling
class compat_HTMLParseError(Exception):
pass

4
youtube_dlc/downloader/http.py
View File

@ -109,7 +109,9 @@ class HttpFD(FileDownloader):
try:
ctx.data = self.ydl.urlopen(request)
except (compat_urllib_error.URLError, ) as err:
if isinstance(err.reason, socket.timeout):
# reason may not be available, e.g. for urllib2.HTTPError on python 2.6
reason = getattr(err, 'reason', None)
if isinstance(reason, socket.timeout):
raise RetryDownload(err)
raise err
# When trying to resume, Content-Range HTTP header of response has to be checked

103
youtube_dlc/extractor/amara.py Normal file
View File

@ -0,0 +1,103 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .youtube import YoutubeIE
from .vimeo import VimeoIE
from ..utils import (
int_or_none,
parse_iso8601,
update_url_query,
)
class AmaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amara\.org/(?:\w+/)?videos/(?P<id>\w+)'
_TESTS = [{
# Youtube
'url': 'https://amara.org/en/videos/jVx79ZKGK1ky/info/why-jury-trials-are-becoming-less-common/?tab=video',
'md5': 'ea10daf2b6154b8c1ecf9922aca5e8ae',
'info_dict': {
'id': 'h6ZuVdvYnfE',
'ext': 'mp4',
'title': 'Why jury trials are becoming less common',
'description': 'md5:a61811c319943960b6ab1c23e0cbc2c1',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20160813',
'uploader': 'PBS NewsHour',
'uploader_id': 'PBSNewsHour',
'timestamp': 1549639570,
}
}, {
# Vimeo
'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011',
'md5': '99392c75fa05d432a8f11df03612195e',
'info_dict': {
'id': '18622084',
'ext': 'mov',
'title': 'Vimeo at CES 2011!',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'timestamp': 1294763658,
'upload_date': '20110111',
'uploader': 'Sam Morrill',
'uploader_id': 'sammorrill'
}
}, {
# Direct Link
'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/',
'md5': 'd3970f08512738ee60c5807311ff5d3f',
'info_dict': {
'id': 's8KL7I3jLmh6',
'ext': 'mp4',
'title': 'The danger of a single story',
'description': 'md5:d769b31139c3b8bb5be9177f62ea3f23',
'thumbnail': r're:^https?://.*\.jpg$',
'subtitles': dict,
'upload_date': '20091007',
'timestamp': 1254942511,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(
'https://amara.org/api/videos/%s/' % video_id,
video_id, query={'format': 'json'})
title = meta['title']
video_url = meta['all_urls'][0]
subtitles = {}
for language in (meta.get('languages') or []):
subtitles_uri = language.get('subtitles_uri')
if not (subtitles_uri and language.get('published')):
continue
subtitle = subtitles.setdefault(language.get('code') or 'en', [])
for f in ('json', 'srt', 'vtt'):
subtitle.append({
'ext': f,
'url': update_url_query(subtitles_uri, {'format': f}),
})
info = {
'url': video_url,
'id': video_id,
'subtitles': subtitles,
'title': title,
'description': meta.get('description'),
'thumbnail': meta.get('thumbnail'),
'duration': int_or_none(meta.get('duration')),
'timestamp': parse_iso8601(meta.get('created')),
}
for ie in (YoutubeIE, VimeoIE):
if ie.suitable(video_url):
info.update({
'_type': 'url_transparent',
'ie_key': ie.ie_key(),
})
break
return info

8
youtube_dlc/extractor/brightcove.py
View File

@ -147,7 +147,7 @@ class BrightcoveLegacyIE(InfoExtractor):
]
@classmethod
def _build_brighcove_url(cls, object_str):
def _build_brightcove_url(cls, object_str):
"""
Build a Brightcove url from a xml string containing
<object class="BrightcoveExperience">{params}</object>
@ -217,7 +217,7 @@ class BrightcoveLegacyIE(InfoExtractor):
return cls._make_brightcove_url(params)
@classmethod
def _build_brighcove_url_from_js(cls, object_js):
def _build_brightcove_url_from_js(cls, object_js):
# The layout of JS is as follows:
# customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
# // build Brightcove <object /> XML
@ -272,12 +272,12 @@ class BrightcoveLegacyIE(InfoExtractor):
).+?>\s*</object>''',
webpage)
if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
return list(filter(None, [cls._build_brightcove_url(m) for m in matches]))
matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)
if matches:
return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
cls._build_brightcove_url_from_js(custom_bc)
for custom_bc in matches]))
return [src for _, src in re.findall(
r'<iframe[^>]+src=([\'"])((?:https?:)?//link\.brightcove\.com/services/player/(?!\1).+)\1', webpage)]

2
youtube_dlc/extractor/common.py
View File

@ -1664,7 +1664,7 @@ class InfoExtractor(object):
# just the media without qualities renditions.
# Fortunately, master playlist can be easily distinguished from media
# playlist based on particular tags availability. As of [1, 4.3.3, 4.3.4]
# master playlist tags MUST NOT appear in a media playist and vice versa.
# master playlist tags MUST NOT appear in a media playlist and vice versa.
# As of [1, 4.3.3.1] #EXT-X-TARGETDURATION tag is REQUIRED for every
# media playlist and MUST NOT appear in master playlist thus we can
# clearly detect media playlist with this criterion.

5
youtube_dlc/extractor/discoverynetworks.py
View File

@ -7,7 +7,7 @@ from .dplay import DPlayIE
class DiscoveryNetworksDeIE(DPlayIE):
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show|sendungen)/(?P<programme>[^/]+)/(?:video/)?(?P<alternate_id>[^/]+)'
_TESTS = [{
'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100',
@ -29,6 +29,9 @@ class DiscoveryNetworksDeIE(DPlayIE):
}, {
'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B',
'only_matching': True,
}, {
'url': 'https://tlc.de/sendungen/breaking-amish/die-welt-da-drauen/',
'only_matching': True,
}]
def _real_extract(self, url):

4
youtube_dlc/extractor/europa.py
View File

@ -60,7 +60,7 @@ class EuropaIE(InfoExtractor):
title = get_item('title', preferred_langs) or video_id
description = get_item('description', preferred_langs)
thumbnmail = xpath_text(playlist, './info/thumburl', 'thumbnail')
thumbnail = xpath_text(playlist, './info/thumburl', 'thumbnail')
upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date'))
duration = parse_duration(xpath_text(playlist, './info/duration', 'duration'))
view_count = int_or_none(xpath_text(playlist, './info/views', 'views'))
@ -85,7 +85,7 @@ class EuropaIE(InfoExtractor):
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnmail,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,

2
youtube_dlc/extractor/extractors.py
View File

@ -36,6 +36,7 @@ from .afreecatv import AfreecaTVIE
from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .amara import AmaraIE
from .alura import (
AluraIE,
AluraCourseIE
@ -1507,7 +1508,6 @@ from .youtube import (
YoutubeIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
YoutubeLiveIE,
YoutubeTabIE,
YoutubePlaylistIE,
YoutubeRecommendedIE,

2
youtube_dlc/extractor/francetv.py
View File

@ -211,7 +211,7 @@ class FranceTVIE(InfoExtractor):
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': clean_html(info.get('synopsis')),
'thumbnail': urljoin('http://pluzz.francetv.fr', info.get('image')),
'thumbnail': urljoin('https://sivideo.webservices.francetelevisions.fr', info.get('image')),
'duration': int_or_none(info.get('real_duration')) or parse_duration(info.get('duree')),
'timestamp': int_or_none(try_get(info, lambda x: x['diffusion']['timestamp'])),
'is_live': is_live,

2
youtube_dlc/extractor/generic.py
View File

@ -842,7 +842,7 @@ class GenericIE(InfoExtractor):
'skip_download': True,
}
},
# MTVSercices embed
# MTVServices embed
{
'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
'md5': 'ca1aef97695ef2c1d6973256a57e5252',

58
youtube_dlc/extractor/googledrive.py
View File

@ -3,11 +3,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
lowercase_escape,
try_get,
update_url_query,
)
@ -38,21 +40,10 @@ class GoogleDriveIE(InfoExtractor):
# video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
'info_dict': {
'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
'ext': 'mp4',
'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
}
'only_matching': True,
}, {
# video id is longer than 28 characters
'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
'info_dict': {
'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
'ext': 'mp4',
'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
'duration': 189,
},
'only_matching': True,
}, {
'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
@ -171,23 +162,21 @@ class GoogleDriveIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id)
video_info = compat_parse_qs(self._download_webpage(
'https://drive.google.com/get_video_info',
video_id, query={'docid': video_id}))
title = self._search_regex(
r'"title"\s*,\s*"([^"]+)', webpage, 'title',
default=None) or self._og_search_title(webpage)
duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
default=None))
def get_value(key):
return try_get(video_info, lambda x: x[key][0])
reason = get_value('reason')
title = get_value('title')
if not title and reason:
raise ExtractorError(reason, expected=True)
formats = []
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
'fmt stream map', default='').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage,
'fmt_list', default='').split(',')
fmt_stream_map = (get_value('fmt_stream_map') or '').split(',')
fmt_list = (get_value('fmt_list') or '').split(',')
if fmt_stream_map and fmt_list:
resolutions = {}
for fmt in fmt_list:
@ -257,19 +246,14 @@ class GoogleDriveIE(InfoExtractor):
if urlh and urlh.headers.get('Content-Disposition'):
add_source_format(urlh)
if not formats:
reason = self._search_regex(
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason, expected=True)
if not formats and reason:
raise ExtractorError(reason, expected=True)
self._sort_formats(formats)
hl = self._search_regex(
r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
hl = get_value('hl')
subtitles_id = None
ttsurl = self._search_regex(
r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
ttsurl = get_value('ttsurl')
if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl
# query string
@ -281,8 +265,8 @@ class GoogleDriveIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'thumbnail': 'https://drive.google.com/thumbnail?id=' + video_id,
'duration': int_or_none(get_value('length_seconds')),
'formats': formats,
'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
'automatic_captions': self.extract_automatic_captions(

7
youtube_dlc/extractor/infoq.py
View File

@ -54,7 +54,7 @@ class InfoQIE(BokeCCBaseIE):
def _extract_rtmp_video(self, webpage):
# The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/'
video_url = 'rtmpe://videof.infoq.com/cfx/st/'
# Extract video URL
encoded_id = self._search_regex(
@ -86,17 +86,18 @@ class InfoQIE(BokeCCBaseIE):
return [{
'format_id': 'http_video',
'url': http_video_url,
'http_headers': {'Referer': 'https://www.infoq.com/'},
}]
def _extract_http_audio(self, webpage, video_id):
fields = self._hidden_inputs(webpage)
fields = self._form_hidden_inputs('mp3Form', webpage)
http_audio_url = fields.get('filename')
if not http_audio_url:
return []
# base URL is found in the Location header in the response returned by
# GET https://www.infoq.com/mp3download.action?filename=... when logged in.
http_audio_url = compat_urlparse.urljoin('http://res.infoq.com/downloads/mp3downloads/', http_audio_url)
http_audio_url = compat_urlparse.urljoin('http://ress.infoq.com/downloads/mp3downloads/', http_audio_url)
http_audio_url = update_url_query(http_audio_url, self._extract_cf_auth(webpage))
# audio file seem to be missing some times even if there is a download link

4
youtube_dlc/extractor/kusi.py
View File

@ -64,7 +64,7 @@ class KUSIIE(InfoExtractor):
duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000)
description = xpath_text(doc, 'ABSTRACT')
thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME')
createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
creation_time = timeconvert(xpath_text(doc, 'rfc822creationdate'))
quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
formats = []
@ -84,5 +84,5 @@ class KUSIIE(InfoExtractor):
'duration': duration,
'formats': formats,
'thumbnail': thumbnail,
'timestamp': createtion_time,
'timestamp': creation_time,
}

2
youtube_dlc/extractor/npr.py
View File

@ -33,7 +33,7 @@ class NprIE(InfoExtractor):
},
}],
}, {
# mutlimedia, not media title
# multimedia, not media title
'url': 'https://www.npr.org/2017/06/19/533198237/tigers-jaw-tiny-desk-concert',
'info_dict': {
'id': '533198237',

2
youtube_dlc/extractor/pbs.py
View File

@ -477,7 +477,7 @@ class PBSIE(InfoExtractor):
if media_id:
return media_id, presumptive_id, upload_date, description
# Fronline video embedded via flp
# Frontline video embedded via flp
video_id = self._search_regex(
r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
if video_id:

132
youtube_dlc/extractor/rai.py
View File

@ -16,8 +16,9 @@ from ..utils import (
GeoRestrictedError,
int_or_none,
parse_duration,
remove_start,
strip_or_none,
unescapeHTML,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
@ -67,7 +68,7 @@ class RaiBaseIE(InfoExtractor):
# This does not imply geo restriction (e.g.
# http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
if media_url == 'http://download.rai.it/video_no_available.mp4':
if '/video_no_available.mp4' in media_url:
continue
ext = determine_ext(media_url)
@ -122,27 +123,8 @@ class RaiBaseIE(InfoExtractor):
class RaiPlayIE(RaiBaseIE):
_VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.(?:html|json))' % RaiBaseIE._UUID_RE
_VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
_TESTS = [{
'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
'md5': '340aa3b7afb54bfd14a8c11786450d76',
'info_dict': {
'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
'ext': 'mp4',
'title': 'La Casa Bianca',
'alt_title': 'S2016 - Puntata del 23/10/2016',
'description': 'md5:a09d45890850458077d1f68bb036e0a5',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 3',
'creator': 'Rai 3',
'duration': 3278,
'timestamp': 1477764300,
'upload_date': '20161029',
'series': 'La Casa Bianca',
'season': '2016',
},
'skip': 'This content is not available',
}, {
'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': '8970abf8caf8aef4696e7b1f2adfc696',
'info_dict': {
@ -166,10 +148,10 @@ class RaiPlayIE(RaiBaseIE):
}]
def _real_extract(self, url):
url, video_id = re.match(self._VALID_URL, url).groups()
base, video_id = re.match(self._VALID_URL, url).groups()
media = self._download_json(
url.replace('.html', '.json'), video_id, 'Downloading video JSON')
base + '.json', video_id, 'Downloading video JSON')
title = media['name']
video = media['video']
@ -195,7 +177,8 @@ class RaiPlayIE(RaiBaseIE):
season = media.get('season')
info = {
'id': video_id,
'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
'display_id': video_id,
'title': self._live_title(title) if relinker_info.get(
'is_live') else title,
'alt_title': strip_or_none(media.get('subtitle')),
@ -217,16 +200,16 @@ class RaiPlayIE(RaiBaseIE):
return info
class RaiPlayLiveIE(RaiBaseIE):
_VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+)'
_TEST = {
class RaiPlayLiveIE(RaiPlayIE):
_VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'http://www.raiplay.it/dirette/rainews24',
'info_dict': {
'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
'display_id': 'rainews24',
'ext': 'mp4',
'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:6eca31500550f9376819f174e5644754',
'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
'uploader': 'Rai News 24',
'creator': 'Rai News 24',
'is_live': True,
@ -234,58 +217,50 @@ class RaiPlayLiveIE(RaiBaseIE):
'params': {
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE,
webpage, 'content id')
return {
'_type': 'url_transparent',
'ie_key': RaiPlayIE.ie_key(),
'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id,
'id': video_id,
'display_id': display_id,
}
}]
class RaiPlayPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
_VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
'info_dict': {
'id': 'nondirloalmiocapo',
'title': 'Non dirlo al mio capo',
'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86',
'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
},
'playlist_mincount': 12,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
base, playlist_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_meta(
('programma', 'nomeProgramma'), webpage, 'title')
description = unescapeHTML(self._html_search_meta(
('description', 'og:description'), webpage, 'description'))
program = self._download_json(
base + '.json', playlist_id, 'Downloading program JSON')
entries = []
for mobj in re.finditer(
r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1',
webpage):
video_url = urljoin(url, mobj.group('path'))
entries.append(self.url_result(
video_url, ie=RaiPlayIE.ie_key(),
video_id=RaiPlayIE._match_id(video_url)))
for b in (program.get('blocks') or []):
for s in (b.get('sets') or []):
s_id = s.get('id')
if not s_id:
continue
medias = self._download_json(
'%s/%s.json' % (base, s_id), s_id,
'Downloading content set JSON', fatal=False)
if not medias:
continue
for m in (medias.get('items') or []):
path_id = m.get('path_id')
if not path_id:
continue
video_url = urljoin(url, path_id)
entries.append(self.url_result(
video_url, ie=RaiPlayIE.ie_key(),
video_id=RaiPlayIE._match_id(video_url)))
return self.playlist_result(entries, playlist_id, title, description)
return self.playlist_result(
entries, playlist_id, program.get('name'),
try_get(program, lambda x: x['program_info']['description']))
class RaiIE(RaiBaseIE):
@ -328,19 +303,6 @@ class RaiIE(RaiBaseIE):
'duration': 2214,
'upload_date': '20161103',
}
}, {
# drawMediaRaiTV(...)
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
'md5': '2dd727e61114e1ee9c47f0da6914e178',
'info_dict': {
'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
'ext': 'mp4',
'title': 'Il pacco',
'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20141221',
},
'skip': 'This content is not available',
}, {
# initEdizione('ContentItem-...'
'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
@ -352,18 +314,6 @@ class RaiIE(RaiBaseIE):
'upload_date': '20170401',
},
'skip': 'Changes daily',
}, {
# HDS live stream with only relinker URL
'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
'info_dict': {
'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
'ext': 'flv',
'title': 'EuroNews',
},
'params': {
'skip_download': True,
},
'skip': 'This content is available only in Italy',
}, {
# HLS live stream with ContentItem in og:url
'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
@ -473,7 +423,7 @@ class RaiIE(RaiBaseIE):
except ExtractorError:
pass
relinker_url = self._search_regex(
relinker_url = self._proto_relative_url(self._search_regex(
r'''(?x)
(?:
var\s+videoURL|
@ -485,7 +435,7 @@ class RaiIE(RaiBaseIE):
//mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
(?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
''',
webpage, 'relinker URL', group='url')
webpage, 'relinker URL', group='url'))
relinker_info = self._extract_relinker_info(
urljoin(url, relinker_url), video_id)

2
youtube_dlc/extractor/soundcloud.py
View File

@ -649,7 +649,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
def _extract_playlist(self, base_url, playlist_id, playlist_title):
# Per the SoundCloud documentation, the maximum limit for a linked partioning query is 200.
# Per the SoundCloud documentation, the maximum limit for a linked partitioning query is 200.
# https://developers.soundcloud.com/blog/offset-pagination-deprecated
COMMON_QUERY = {
'limit': 200,

48
youtube_dlc/extractor/svt.py
View File

@ -9,6 +9,7 @@ from ..utils import (
determine_ext,
dict_get,
int_or_none,
unified_timestamp,
str_or_none,
strip_or_none,
try_get,
@ -44,7 +45,8 @@ class SVTBaseIE(InfoExtractor):
'format_id': player_type,
'url': vurl,
})
if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
rights = try_get(video_info, lambda x: x['rights'], dict) or {}
if not formats and rights.get('geoBlockedSweden'):
self.raise_geo_restricted(
'This video is only available in Sweden',
countries=self._GEO_COUNTRIES)
@ -70,6 +72,7 @@ class SVTBaseIE(InfoExtractor):
episode = video_info.get('episodeTitle')
episode_number = int_or_none(video_info.get('episodeNumber'))
timestamp = unified_timestamp(rights.get('validFrom'))
duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
age_limit = None
adult = dict_get(
@ -84,6 +87,7 @@ class SVTBaseIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
'duration': duration,
'timestamp': timestamp,
'age_limit': age_limit,
'series': series,
'season_number': season_number,
@ -136,26 +140,39 @@ class SVTPlayIE(SVTPlayBaseIE):
IE_DESC = 'SVT Play and Öppet arkiv'
_VALID_URL = r'''(?x)
(?:
svt:(?P<svt_id>[^/?#&]+)|
(?:
svt:|
https?://(?:www\.)?svt\.se/barnkanalen/barnplay/[^/]+/
)
(?P<svt_id>[^/?#&]+)|
https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
)
'''
_TESTS = [{
'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
'url': 'https://www.svtplay.se/video/26194546/det-har-ar-himlen',
'md5': '2382036fd6f8c994856c323fe51c426e',
'info_dict': {
'id': '5996901',
'id': 'jNwpV9P',
'ext': 'mp4',
'title': 'Flygplan till Haile Selassie',
'duration': 3527,
'thumbnail': r're:^https?://.*[\.-]jpg$',
'title': 'Det här är himlen',
'timestamp': 1586044800,
'upload_date': '20200405',
'duration': 3515,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
'age_limit': 0,
'subtitles': {
'sv': [{
'ext': 'wsrt',
'ext': 'vtt',
}]
},
},
'params': {
'format': 'bestvideo',
# skip for now due to download test asserts that segment is > 10000 bytes and svt uses
# init segments that are smaller
# AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B
'skip_download': True,
},
}, {
# geo restricted to Sweden
'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
@ -172,6 +189,12 @@ class SVTPlayIE(SVTPlayBaseIE):
}, {
'url': 'svt:14278044',
'only_matching': True,
}, {
'url': 'https://www.svt.se/barnkanalen/barnplay/kar/eWv5MLX/',
'only_matching': True,
}, {
'url': 'svt:eWv5MLX',
'only_matching': True,
}]
def _adjust_title(self, info):
@ -236,7 +259,10 @@ class SVTPlayIE(SVTPlayBaseIE):
r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'),
webpage, 'video id')
return self._extract_by_video_id(svt_id, webpage)
info_dict = self._extract_by_video_id(svt_id, webpage)
info_dict['thumbnail'] = thumbnail
return info_dict
class SVTSeriesIE(SVTPlayBaseIE):
@ -360,7 +386,7 @@ class SVTPageIE(InfoExtractor):
@classmethod
def suitable(cls, url):
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
def _real_extract(self, url):
path, display_id = re.match(self._VALID_URL, url).groups()

2
youtube_dlc/extractor/tagesschau.py
View File

@ -86,7 +86,7 @@ class TagesschauPlayerIE(InfoExtractor):
# return self._extract_via_api(kind, video_id)
# JSON api does not provide some audio formats (e.g. ogg) thus
# extractiong audio via webpage
# extracting audio via webpage
webpage = self._download_webpage(url, video_id)

2
youtube_dlc/extractor/theplatform.py
View File

@ -208,7 +208,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
if m:
return [m.group('url')]
# Are whitesapces ignored in URLs?
# Are whitespaces ignored in URLs?
# https://github.com/ytdl-org/youtube-dl/issues/12044
matches = re.findall(
r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage)

6
youtube_dlc/extractor/turner.py
View File

@ -56,9 +56,9 @@ class TurnerBaseIE(AdobePassIE):
content_id = xpath_text(video_data, 'contentId') or video_id
# rtmp_src = xpath_text(video_data, 'akamai/src')
# if rtmp_src:
# splited_rtmp_src = rtmp_src.split(',')
# if len(splited_rtmp_src) == 2:
# rtmp_src = splited_rtmp_src[1]
# split_rtmp_src = rtmp_src.split(',')
# if len(split_rtmp_src) == 2:
# rtmp_src = split_rtmp_src[1]
# aifp = xpath_text(video_data, 'akamai/aifp', default='')
urls = []

171
youtube_dlc/extractor/viki.py
View File

@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import hashlib
import hmac
import itertools
@ -9,6 +10,10 @@ import re
import time
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
@ -166,19 +171,20 @@ class VikiIE(VikiBaseIE):
}, {
# episode
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
'md5': '5fa476a902e902783ac7a4d615cdbc7a',
'md5': '94e0e34fd58f169f40c184f232356cfe',
'info_dict': {
'id': '44699v',
'ext': 'mp4',
'title': 'Boys Over Flowers - Episode 1',
'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
'duration': 4204,
'duration': 4172,
'timestamp': 1270496524,
'upload_date': '20100405',
'uploader': 'group8',
'like_count': int,
'age_limit': 13,
}
},
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
}, {
# youtube external
'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
@ -195,14 +201,15 @@ class VikiIE(VikiBaseIE):
'uploader_id': 'ad14065n',
'like_count': int,
'age_limit': 13,
}
},
'skip': 'Page not found!',
}, {
'url': 'http://www.viki.com/player/44699v',
'only_matching': True,
}, {
# non-English description
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
'md5': '1713ae35df5a521b31f6dc40730e7c9c',
'md5': 'adf9e321a0ae5d0aace349efaaff7691',
'info_dict': {
'id': '158036v',
'ext': 'mp4',
@ -218,71 +225,11 @@ class VikiIE(VikiBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._call_api(
'videos/%s.json' % video_id, video_id, 'Downloading video JSON')
streams = self._call_api(
'videos/%s/streams.json' % video_id, video_id,
'Downloading video streams JSON')
formats = []
for format_id, stream_dict in streams.items():
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None))
for protocol, format_dict in stream_dict.items():
# rtmps URLs does not seem to work
if protocol == 'rtmps':
continue
format_url = format_dict.get('url')
format_drms = format_dict.get('drms')
format_stream_id = format_dict.get('id')
if format_id == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native',
m3u8_id='m3u8-%s' % protocol, fatal=False)
# Despite CODECS metadata in m3u8 all video-only formats
# are actually video+audio
for f in m3u8_formats:
if f.get('acodec') == 'none' and f.get('vcodec') != 'none':
f['acodec'] = None
formats.extend(m3u8_formats)
elif format_id == 'mpd':
mpd_formats = self._extract_mpd_formats(
format_url, video_id,
mpd_id='mpd-%s' % protocol, fatal=False)
formats.extend(mpd_formats)
elif format_id == 'mpd':
formats.extend(mpd_formats)
elif format_url.startswith('rtmp'):
mobj = re.search(
r'^(?P<url>rtmp://[^/]+/(?P<app>.+?))/(?P<playpath>mp4:.+)$',
format_url)
if not mobj:
continue
formats.append({
'format_id': 'rtmp-%s' % format_id,
'ext': 'flv',
'url': mobj.group('url'),
'play_path': mobj.group('playpath'),
'app': mobj.group('app'),
'page_url': url,
'drms': format_drms,
'stream_id': format_stream_id,
})
else:
urlh = self._request_webpage(
HEADRequest(format_url), video_id, 'Checking file size', fatal=False)
formats.append({
'url': format_url,
'format_id': '%s-%s' % (format_id, protocol),
'height': height,
'drms': format_drms,
'stream_id': format_stream_id,
'filesize': int_or_none(urlh.headers.get('Content-Length')),
})
self._sort_formats(formats)
resp = self._download_json(
'https://www.viki.com/api/videos/' + video_id,
video_id, 'Downloading video JSON',
headers={'x-viki-app-ver': '4.0.57'})
video = resp['video']
self._check_errors(video)
@ -342,12 +289,84 @@ class VikiIE(VikiBaseIE):
'subtitles': subtitles,
}
if 'external' in streams:
result.update({
'_type': 'url_transparent',
'url': streams['external']['url'],
})
return result
formats = []
def add_format(format_id, format_dict, protocol='http'):
# rtmps URLs does not seem to work
if protocol == 'rtmps':
return