gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[generic] Simplify playlist support (#2948)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-08-22 18:19:56 +02:00
parent be843678b1
commit ed2d6a1960
1 changed files with 22 additions and 43 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

65
youtube_dl/extractor/generic.py
View file

@ -16,6 +16,7 @@ from ..utils import (
ExtractorError, ExtractorError,
HEADRequest, HEADRequest,
orderedSet,
parse_xml, parse_xml,
smuggle_url, smuggle_url,
unescapeHTML, unescapeHTML,
@ -292,15 +293,17 @@ class GenericIE(InfoExtractor):
# YouTube embed via <data-embed-url=""> # YouTube embed via <data-embed-url="">
{ {
'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
'md5': 'c267b1ab6d736057d64babaa37e07a66',
'info_dict': { 'info_dict': {
'id': 'Ybd-qmqYYpA', 'id': 'jpSGZsgga_I',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Asphalt 8: Airborne - Chinese Great Wall - Android Game Trailer', 'title': 'Asphalt 8: Airborne - Launch Trailer',
'uploader': 'gameloftandroid', 'uploader': 'Gameloft',
'uploader_id': 'gameloftandroid', 'uploader_id': 'gameloft',
'upload_date': '20140321', 'upload_date': '20130821',
'description': 'md5:9c6dca5dd75b7131ce482ccf080749d6' 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a',
},
'params': {
'skip_download': True,
} }
} }
] ]
@ -493,6 +496,12 @@ class GenericIE(InfoExtractor):
video_uploader = self._search_regex( video_uploader = self._search_regex(
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
# Helper method
def _playlist_from_matches(matches, getter, ie=None):
urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches)
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for BrightCove: # Look for BrightCove:
bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
if bc_urls: if bc_urls:
@ -537,35 +546,15 @@ class GenericIE(InfoExtractor):
(?:embed|v)/.+?) (?:embed|v)/.+?)
\1''', webpage) \1''', webpage)
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') return _playlist_from_matches(
for tuppl in matches] matches, lambda m: unescapeHTML(m[1]), ie='Youtube')
# 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(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for embedded Dailymotion player # Look for embedded Dailymotion player
matches = re.findall( matches = re.findall(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(tuppl[1])) return _playlist_from_matches(
for tuppl in matches] matches, lambda m: unescapeHTML(m[1]))
# 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(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for embedded Wistia player # Look for embedded Wistia player
match = re.search( match = re.search(
@ -679,18 +668,8 @@ class GenericIE(InfoExtractor):
# Look for funnyordie embed # Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
if matches: if matches:
urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie') return _playlist_from_matches(
for eurl in matches] matches, getter=unescapeHTML, ie='FunnyOrDie')
# 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(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for embedded RUTV player # Look for embedded RUTV player
rutv_url = RUTVIE._extract_url(webpage) rutv_url = RUTVIE._extract_url(webpage)