Allow users to specify an age limit (fixes #1545)

With these changes, users can now restrict what videos are downloaded by the intented audience, by specifying their age with --age-limit YEARS .
Add rudimentary support in youtube, pornotube, and youporn.
This commit is contained in:
Philipp Hagemeister 2013-10-06 06:06:30 +02:00
parent f4aac741d5
commit 8dbe9899a9
7 changed files with 81 additions and 3 deletions

View file

@ -54,6 +54,7 @@ class InfoExtractor(object):
view_count: How many users have watched the video on the platform.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
age_limit: Age restriction for the video, as an integer (years)
formats: A list of dictionaries for each format available, it must
be ordered from worst to best quality. Potential fields:
* url Mandatory. The URL of the video file
@ -318,6 +319,15 @@ class InfoExtractor(object):
self._og_regex('video')],
html, name, **kargs)
def _rta_search(self, html):
# See http://www.rtalabel.org/index.php?content=howtofaq#single
if re.search(r'(?ix)<meta\s+name="rating"\s+'
r' content="RTA-5042-1996-1400-1577-RTA"',
html):
return 18
return 0
class SearchInfoExtractor(InfoExtractor):
"""
Base class for paged search queries extractors.

View file

@ -38,6 +38,7 @@ class PornotubeIE(InfoExtractor):
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
if upload_date: upload_date = unified_strdate(upload_date)
age_limit = self._rta_search(webpage)
info = {'id': video_id,
'url': video_url,
@ -45,6 +46,7 @@ class PornotubeIE(InfoExtractor):
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
'format': 'flv'}
'format': 'flv',
'age_restriction': age_limit}
return [info]

View file

@ -51,6 +51,7 @@ class YouPornIE(InfoExtractor):
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
age_limit = self._rta_search(webpage)
# Get JSON parameters
json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
@ -115,7 +116,8 @@ class YouPornIE(InfoExtractor):
'ext': extension,
'format': format,
'thumbnail': thumbnail,
'description': video_description
'description': video_description,
'age_restriction': age_limit,
})
if self._downloader.params.get('listformats', None):

View file

@ -1495,7 +1495,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'description': video_description,
'player_url': player_url,
'subtitles': video_subtitles,
'duration': video_duration
'duration': video_duration,
'age_restriction': 18 if age_gate else 0,
})
return results