aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/byutv.py2
-rw-r--r--youtube_dl/extractor/canalplus.py14
-rw-r--r--youtube_dl/extractor/odnoklassniki.py5
-rw-r--r--youtube_dl/extractor/screenwavemedia.py9
-rw-r--r--youtube_dl/extractor/worldstarhiphop.py23
5 files changed, 34 insertions, 19 deletions
diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py
index 6252be05b..3b2de517e 100644
--- a/youtube_dl/extractor/byutv.py
+++ b/youtube_dl/extractor/byutv.py
@@ -16,7 +16,7 @@ class BYUtvIE(InfoExtractor):
'ext': 'mp4',
'description': 'md5:5438d33774b6bdc662f9485a340401cc',
'title': 'Season 5 Episode 5',
- 'thumbnail': 're:^https?://.*promo.*'
+ 'thumbnail': 're:^https?://.*\.jpg$'
},
'params': {
'skip_download': True,
diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py
index 1b14471e5..699b4f7d0 100644
--- a/youtube_dl/extractor/canalplus.py
+++ b/youtube_dl/extractor/canalplus.py
@@ -25,14 +25,14 @@ class CanalplusIE(InfoExtractor):
}
_TESTS = [{
- 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
- 'md5': '3db39fb48b9685438ecf33a1078023e4',
+ 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+ 'md5': 'b3481d7ca972f61e37420798d0a9d934',
'info_dict': {
- 'id': '922470',
+ 'id': '1263092',
'ext': 'flv',
- 'title': 'Zapping - 26/08/13',
- 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
- 'upload_date': '20130826',
+ 'title': 'Le Zapping - 13/05/15',
+ 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+ 'upload_date': '20150513',
},
}, {
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
@@ -56,7 +56,7 @@ class CanalplusIE(InfoExtractor):
'skip': 'videos get deleted after a while',
}, {
'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
- 'md5': '65aa83ad62fe107ce29e564bb8712580',
+ 'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
'info_dict': {
'id': '1213714',
'ext': 'flv',
diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
index 155d0ee6a..fbc521d1a 100644
--- a/youtube_dl/extractor/odnoklassniki.py
+++ b/youtube_dl/extractor/odnoklassniki.py
@@ -6,6 +6,7 @@ from ..utils import (
unified_strdate,
int_or_none,
qualities,
+ unescapeHTML,
)
@@ -36,8 +37,8 @@ class OdnoklassnikiIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
- self._search_regex(
- r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'),
+ unescapeHTML(self._search_regex(
+ r'data-attributes="([^"]+)"', webpage, 'player')),
video_id)
metadata = self._parse_json(player['flashvars']['metadata'], video_id)
diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py
index 74fb1983a..d1ab66b32 100644
--- a/youtube_dl/extractor/screenwavemedia.py
+++ b/youtube_dl/extractor/screenwavemedia.py
@@ -11,7 +11,7 @@ from ..utils import (
class ScreenwaveMediaIE(InfoExtractor):
- _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
+ _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
_TESTS = [{
'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
@@ -20,7 +20,10 @@ class ScreenwaveMediaIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
- playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
+
+ playerdata = self._download_webpage(
+ 'http://player.screenwavemedia.com/play/player.php?id=%s' % video_id,
+ video_id, 'Downloading player webpage')
vidtitle = self._search_regex(
r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
@@ -99,7 +102,7 @@ class TeamFourIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
playerdata_url = self._search_regex(
- r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+ r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
webpage, 'player data URL')
video_title = self._html_search_regex(
diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py
index d5c26a032..a3ea26feb 100644
--- a/youtube_dl/extractor/worldstarhiphop.py
+++ b/youtube_dl/extractor/worldstarhiphop.py
@@ -6,8 +6,8 @@ from .common import InfoExtractor
class WorldStarHipHopIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
- _TEST = {
+ _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?v=(?P<id>.*)'
+ _TESTS = [{
"url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
"md5": "9d04de741161603bf7071bbf4e883186",
"info_dict": {
@@ -15,7 +15,15 @@ class WorldStarHipHopIE(InfoExtractor):
"ext": "mp4",
"title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
}
- }
+ }, {
+ 'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
+ 'md5': 'dc1c76c83ecc4190bb1eb143899b87d3',
+ 'info_dict': {
+ 'id': 'wshh6a7q1ny0G34ZwuIO',
+ 'ext': 'mp4',
+ "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
+ }
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -26,19 +34,22 @@ class WorldStarHipHopIE(InfoExtractor):
return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
video_url = self._search_regex(
- r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL')
+ [r'so\.addVariable\("file","(.*?)"\)',
+ r'<div class="artlist">\s*<a[^>]+href="([^"]+)">'],
+ webpage, 'video URL')
if 'youtube' in video_url:
return self.url_result(video_url, ie='Youtube')
video_title = self._html_search_regex(
- r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
+ [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
+ r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
webpage, 'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(
r'rel="image_src" href="(.*)" />', webpage, 'thumbnail',
- fatal=False)
+ default=None)
if not thumbnail:
_title = r'candytitles.*>(.*)</span>'
mobj = re.search(_title, webpage)
generated by cgit v1.2.3 (git 2.25.1) at 2025-07-23 18:08:18 +0000