mirrors/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-24 23:26:25 +00:00
Code Issues Projects Releases Wiki Activity

Merge remote-tracking branch 'anovicecodemonkey/generic-data-video-url'

Browse Source 
Conflicts:
	youtube_dl/extractor/generic.py
This commit is contained in:
Philipp Hagemeister 2014-08-22 17:40:36 +02:00
commit c71dfccc98
1 changed files with 39 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/extractor/generic.py
View File

@ -289,6 +289,20 @@ class GenericIE(InfoExtractor):
'description': 'Mario\'s life in the fast lane has never looked so good.', 'description': 'Mario\'s life in the fast lane has never looked so good.',
}, },
}, },
# YouTube embed via <data-embed-url="">
{
'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
'md5': 'c267b1ab6d736057d64babaa37e07a66',
'info_dict': {
'id': 'Ybd-qmqYYpA',
'ext': 'mp4',
'title': 'Asphalt 8: Airborne - Chinese Great Wall - Android Game Trailer',
'uploader': 'gameloftandroid',
'uploader_id': 'gameloftandroid',
'upload_date': '20140321',
'description': 'md5:9c6dca5dd75b7131ce482ccf080749d6'
}
}
] ]
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
@ -514,6 +528,7 @@ class GenericIE(InfoExtractor):
matches = re.findall(r'''(?x) matches = re.findall(r'''(?x)
(?: (?:
<iframe[^>]+?src=| <iframe[^>]+?src=|
data-video-url=|
<embed[^>]+?src=| <embed[^>]+?src=|
embedSWF\(?:\s* embedSWF\(?:\s*
) )
@ -524,6 +539,14 @@ class GenericIE(InfoExtractor):
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
for tuppl in matches] for tuppl in matches]
# First, ensure we have a duplicate free list of entries
seen = set()
new_list = []
theurl = tuple(url.items())
if theurl not in seen:
seen.add(theurl)
new_list.append(url)
urlrs = new_list
return self.playlist_result( return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title) urlrs, playlist_id=video_id, playlist_title=video_title)
@ -533,6 +556,14 @@ class GenericIE(InfoExtractor):
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(tuppl[1])) urlrs = [self.url_result(unescapeHTML(tuppl[1]))
for tuppl in matches] for tuppl in matches]
# First, ensure we have a duplicate free list of entries
seen = set()
new_list = []
theurl = tuple(url.items())
if theurl not in seen:
seen.add(theurl)
new_list.append(url)
urlrs = new_list
return self.playlist_result( return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title) urlrs, playlist_id=video_id, playlist_title=video_title)
@ -650,6 +681,14 @@ class GenericIE(InfoExtractor):
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie') urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
for eurl in matches] for eurl in matches]
# First, ensure we have a duplicate free list of entries
seen = set()
new_list = []
theurl = tuple(url.items())
if theurl not in seen:
seen.add(theurl)
new_list.append(url)
urlrs = new_list
return self.playlist_result( return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title) urlrs, playlist_id=video_id, playlist_title=video_title)