aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/arte.py38
-rw-r--r--youtube_dl/extractor/cinemassacre.py17
-rw-r--r--youtube_dl/extractor/cnn.py2
-rw-r--r--youtube_dl/extractor/crunchyroll.py11
-rw-r--r--youtube_dl/extractor/francetv.py4
-rw-r--r--youtube_dl/extractor/funnyordie.py2
-rw-r--r--youtube_dl/extractor/generic.py17
-rw-r--r--youtube_dl/extractor/mitele.py13
-rw-r--r--youtube_dl/extractor/pbs.py20
-rw-r--r--youtube_dl/extractor/telecinco.py19
-rw-r--r--youtube_dl/extractor/youtube.py5
12 files changed, 107 insertions, 42 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index e0957987c..3023c3095 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -368,6 +368,7 @@ from .teachingchannel import TeachingChannelIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
+from .telecinco import TelecincoIE
from .telemb import TeleMBIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py
index 3a34d1ecc..b9a9440c0 100644
--- a/youtube_dl/extractor/arte.py
+++ b/youtube_dl/extractor/arte.py
@@ -10,8 +10,8 @@ from ..utils import (
unified_strdate,
determine_ext,
get_element_by_id,
- compat_str,
get_element_by_attribute,
+ int_or_none,
)
# There are different sources of video in arte.tv, the extraction process
@@ -90,15 +90,24 @@ class ArteTVPlus7IE(InfoExtractor):
if not upload_date_str:
upload_date_str = player_info.get('VDA', '').split(' ')[0]
+ title = player_info['VTI'].strip()
+ subtitle = player_info.get('VSU', '').strip()
+ if subtitle:
+ title += ' - %s' % subtitle
+
info_dict = {
'id': player_info['VID'],
- 'title': player_info['VTI'],
+ 'title': title,
'description': player_info.get('VDE'),
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
- all_formats = player_info['VSR'].values()
+ all_formats = []
+ for format_id, format_dict in player_info['VSR'].items():
+ fmt = dict(format_dict)
+ fmt['format_id'] = format_id
+ all_formats.append(fmt)
# Some formats use the m3u8 protocol
all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats))
def _match_lang(f):
@@ -149,25 +158,12 @@ class ArteTVPlus7IE(InfoExtractor):
)
formats = sorted(formats, key=sort_key)
def _format(format_info):
- quality = ''
- height = format_info.get('height')
- if height is not None:
- quality = compat_str(height)
- bitrate = format_info.get('bitrate')
- if bitrate is not None:
- quality += '-%d' % bitrate
- if format_info.get('versionCode') is not None:
- format_id = '%s-%s' % (quality, format_info['versionCode'])
- else:
- format_id = quality
- media_type = format_info.get('mediaType')
- if media_type is not None:
- format_id += '-%s' % media_type
info = {
- 'format_id': format_id,
- 'format_note': format_info.get('versionLibelle'),
- 'width': format_info.get('width'),
- 'height': height,
+ 'format_id': format_info['format_id'],
+ 'format_note': '%s, %s' % (format_info.get('versionCode'), format_info.get('versionLibelle')),
+ 'width': int_or_none(format_info.get('width')),
+ 'height': int_or_none(format_info.get('height')),
+ 'tbr': int_or_none(format_info.get('bitrate')),
}
if format_info['mediaType'] == 'rtmp':
info['url'] = format_info['streamer']
diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py
index 496271be4..d064a28f9 100644
--- a/youtube_dl/extractor/cinemassacre.py
+++ b/youtube_dl/extractor/cinemassacre.py
@@ -42,7 +42,7 @@ class CinemassacreIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
- mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+ mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
if not mobj:
raise ExtractorError('Can\'t extract embed url and video id')
playerdata_url = mobj.group('embed_url')
@@ -53,17 +53,22 @@ class CinemassacreIE(InfoExtractor):
video_description = self._html_search_regex(
r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, 'description', flags=re.DOTALL, fatal=False)
+ video_thumbnail = self._og_search_thumbnail(webpage)
playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
- video_thumbnail = self._search_regex(
- r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
- sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
- videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url')
+ vidurl = self._search_regex(
+ r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
+ vidid = self._search_regex(
+ r'\'vidid\'\s*:\s*"([^\']+)"', playerdata, 'vidid')
+ videoserver = self._html_search_regex(
+ r"'videoserver'\s*:\s*'([^']+)'", playerdata, 'videoserver')
+
+ videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
formats = []
- baseurl = sd_url[:sd_url.rfind('/')+1]
+ baseurl = vidurl[:vidurl.rfind('/')+1]
for video in videolist.findall('.//video'):
src = video.get('src')
if not src:
diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py
index dae40c136..78877b1cf 100644
--- a/youtube_dl/extractor/cnn.py
+++ b/youtube_dl/extractor/cnn.py
@@ -12,7 +12,7 @@ from ..utils import (
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
- (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
+ (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index f99888ecc..e3057d900 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -39,6 +39,7 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
'upload_date': '20131013',
+ 'url': 're:(?!.*&amp)',
},
'params': {
# rtmp
@@ -237,12 +238,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
- streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
- video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
- video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+ streamdata = self._download_xml(
+ streamdata_req, video_id,
+ note='Downloading media info for %s' % video_format)
+ video_url = streamdata.find('.//host').text
+ video_play_path = streamdata.find('.//file').text
formats.append({
'url': video_url,
- 'play_path': video_play_path,
+ 'play_path': video_play_path,
'ext': 'flv',
'format': video_format,
'format_id': video_format,
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index 0b3374d97..566e20d76 100644
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -46,7 +46,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
f4m_format['preference'] = 1
formats.extend(f4m_formats)
elif video_url.endswith('.m3u8'):
- formats.extend(self._extract_m3u8_formats(video_url, video_id))
+ formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
elif video_url.startswith('rtmp'):
formats.append({
'url': video_url,
@@ -58,7 +58,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
formats.append({
'url': video_url,
'format_id': format_id,
- 'preference': 2,
+ 'preference': -1,
})
self._sort_formats(formats)
diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py
index d966e8403..ec6d96ada 100644
--- a/youtube_dl/extractor/funnyordie.py
+++ b/youtube_dl/extractor/funnyordie.py
@@ -37,7 +37,7 @@ class FunnyOrDieIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+ links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
if not links:
raise ExtractorError('No media links available for %s' % video_id)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 9057a6beb..9b6498894 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -380,6 +380,17 @@ class GenericIE(InfoExtractor):
'uploader': 'education-portal.com',
},
},
+ {
+ 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
+ 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
+ 'info_dict': {
+ 'id': 'uxjb0lwrcz',
+ 'ext': 'mp4',
+ 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
+ 'duration': 1715.0,
+ 'uploader': 'thoughtworks.wistia.com',
+ },
+ },
]
def report_following_redirect(self, new_url):
@@ -476,7 +487,8 @@ class GenericIE(InfoExtractor):
'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
) % (url, url), expected=True)
else:
- assert ':' in default_search
+ if ':' not in default_search:
+ default_search += ':'
return self.url_result(default_search + url)
url, smuggled_data = unsmuggle_url(url)
@@ -652,7 +664,7 @@ class GenericIE(InfoExtractor):
# Look for embedded Wistia player
match = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+ r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
if match:
embed_url = self._proto_relative_url(
unescapeHTML(match.group('url')))
@@ -664,6 +676,7 @@ class GenericIE(InfoExtractor):
'title': video_title,
'id': video_id,
}
+
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return {
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index 979f3d692..6691521e5 100644
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -6,6 +6,7 @@ import json
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
+ compat_urlparse,
get_element_by_attribute,
parse_duration,
strip_jsonp,
@@ -39,13 +40,21 @@ class MiTeleIE(InfoExtractor):
).replace('\'', '"')
embed_data = json.loads(embed_data_json)
- info_url = embed_data['flashvars']['host']
+ domain = embed_data['mediaUrl']
+ if not domain.startswith('http'):
+ # only happens in telecinco.es videos
+ domain = 'http://' + domain
+ info_url = compat_urlparse.urljoin(
+ domain,
+ compat_urllib_parse.unquote(embed_data['flashvars']['host'])
+ )
info_el = self._download_xml(info_url, episode).find('./video/info')
video_link = info_el.find('videoUrl/link').text
token_query = compat_urllib_parse.urlencode({'id': video_link})
token_info = self._download_json(
- 'http://token.mitele.es/?' + token_query, episode,
+ embed_data['flashvars']['ov_tk'] + '?' + token_query,
+ episode,
transform_source=strip_jsonp
)
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 8f140d626..6118ed5c2 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -80,8 +80,14 @@ class PBSIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140122',
}
+ },
+ {
+ 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
+ 'info_dict': {
+ 'id': 'united-states-of-secrets',
+ },
+ 'playlist_count': 2,
}
-
]
def _extract_webpage(self, url):
@@ -96,6 +102,12 @@ class PBSIE(InfoExtractor):
r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
webpage, 'upload date', default=None))
+ # tabbed frontline videos
+ tabbed_videos = re.findall(
+ r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
+ if tabbed_videos:
+ return tabbed_videos, presumptive_id, upload_date
+
MEDIA_ID_REGEXES = [
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer
@@ -130,6 +142,12 @@ class PBSIE(InfoExtractor):
def _real_extract(self, url):
video_id, display_id, upload_date = self._extract_webpage(url)
+ if isinstance(video_id, list):
+ entries = [self.url_result(
+ 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
+ for vid_id in video_id]
+ return self.playlist_result(entries, display_id)
+
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
info = self._download_json(info_url, display_id)
diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py
new file mode 100644
index 000000000..db9788c18
--- /dev/null
+++ b/youtube_dl/extractor/telecinco.py
@@ -0,0 +1,19 @@
+#coding: utf-8
+from __future__ import unicode_literals
+
+from .mitele import MiTeleIE
+
+
+class TelecincoIE(MiTeleIE):
+ IE_NAME = 'telecinco.es'
+ _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html'
+
+ _TEST = {
+ 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
+ 'info_dict': {
+ 'id': 'MDSVID20141015_0058',
+ 'ext': 'mp4',
+ 'title': 'Con Martín Berasategui, hacer un bacalao al ...',
+ 'duration': 662,
+ },
+ }
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index cfae2de89..4ab56e0ac 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -191,8 +191,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
def _real_initialize(self):
if self._downloader is None:
return
- if not self._set_language():
- return
+ if self._get_login_info()[0] is not None:
+ if not self._set_language():
+ return
if not self._login():
return
self._confirm_age()
generated by cgit v1.2.3 (git 2.26.2) at 2024-07-08 22:25:46 +0000