mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:20:23 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[generic] Automatic detection of flow player and age_limit (Fixes #3576)

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-08-24 05:31:32 +02:00
parent 24e5e24166
commit 4d805e063c
1 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/generic.py
View File

@ -331,6 +331,18 @@ class GenericIE(InfoExtractor):
'info_dict': { 'info_dict': {
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
} }
},
# Flowplayer
{
'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
'md5': '9d65602bf31c6e20014319c7d07fba27',
'info_dict': {
'id': '5123ea6d5e5a7',
'ext': 'mp4',
'age_limit': 18,
'uploader': 'www.handjobhub.com',
'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
}
} }
] ]
@ -570,6 +582,16 @@ def _real_extract(self, url):
r'(?s)<title>(.*?)</title>', webpage, 'video title', r'(?s)<title>(.*?)</title>', webpage, 'video title',
default='video') default='video')
# Try to detect age limit automatically
age_limit = self._rta_search(webpage)
# And then there are the jokers who advertise that they use RTA,
# but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18
# video uploader is domain name # video uploader is domain name
video_uploader = self._search_regex( video_uploader = self._search_regex(
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
@ -833,6 +855,15 @@ def _playlist_from_matches(matches, getter, ie=None):
if not found: if not found:
# Broaden the findall a little bit: JWPlayer JS loader # Broaden the findall a little bit: JWPlayer JS loader
found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
if not found:
# Flow player
found = re.findall(r'''(?xs)
flowplayer\("[^"]+",\s*
\{[^}]+?\}\s*,
\s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
["']?url["']?\s*:\s*["']([^"']+)["']
''', webpage)
assert found
if not found: if not found:
# Try to find twitter cards info # Try to find twitter cards info
found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@ -884,6 +915,7 @@ def check_video(vurl):
'url': video_url, 'url': video_url,
'uploader': video_uploader, 'uploader': video_uploader,
'title': video_title, 'title': video_title,
'age_limit': age_limit,
}) })
if len(entries) == 1: if len(entries) == 1: