lopar/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-11 03:47:34 +00:00
Code Releases Activity

Add agecheck and various improvements to YouPorn IE

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-01-12 16:10:35 +01:00
parent 64ce2aada8
commit 629fcdd135
1 changed files with 18 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
youtube_dl/InfoExtractors.py
View File

@ -3731,12 +3731,8 @@ class UstreamIE(InfoExtractor):
class YouPornIE(InfoExtractor): class YouPornIE(InfoExtractor):
"""Information extractor for youporn.com.""" """Information extractor for youporn.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def _print_formats(self, formats): def _print_formats(self, formats):
"""Print all available formats""" """Print all available formats"""
print(u'Available formats:') print(u'Available formats:')
@ -3759,47 +3755,45 @@ class YouPornIE(InfoExtractor):
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
webpage = self._download_webpage(url, video_id) req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
# Get the video title # Get the video title
VIDEO_TITLE_RE = r'videoTitleArea">(?P<title>.*)</h1>' result = re.search(r'videoTitleArea">(?P<title>.*)</h1>', webpage)
result = re.search(VIDEO_TITLE_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title') raise ExtractorError(u'ERROR: unable to extract video title')
return
video_title = result.group('title').strip() video_title = result.group('title').strip()
# Get the video date # Get the video date
VIDEO_DATE_RE = r'Date:</b>(?P<date>.*)</li>' result = re.search(r'Date:</b>(?P<date>.*)</li>', webpage)
result = re.search(VIDEO_DATE_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract video date') self._downloader.to_stderr(u'WARNING: unable to extract video date')
return upload_date = None
upload_date = result.group('date').strip() else:
upload_date = result.group('date').strip()
# Get the video uploader # Get the video uploader
VIDEO_UPLOADER_RE = r'Submitted:</b>(?P<uploader>.*)</li>' result = re.search(r'Submitted:</b>(?P<uploader>.*)</li>', webpage)
result = re.search(VIDEO_UPLOADER_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract uploader') self._downloader.to_stderr(u'ERROR: unable to extract uploader')
return video_uploader = None
video_uploader = result.group('uploader').strip() else:
video_uploader = clean_html( video_uploader ) video_uploader = result.group('uploader').strip()
video_uploader = clean_html( video_uploader )
# Get all of the formats available # Get all of the formats available
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
result = re.search(DOWNLOAD_LIST_RE, webpage) result = re.search(DOWNLOAD_LIST_RE, webpage)
if result is None: if result is None:
self._downloader.trouble(u'ERROR: unable to extract download list') raise ExtractorError(u'Unable to extract download list')
return
download_list_html = result.group('download_list').strip() download_list_html = result.group('download_list').strip()
# Get all of the links from the page # Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
links = re.findall(LINK_RE, download_list_html) links = re.findall(LINK_RE, download_list_html)
if(len(links) == 0): if(len(links) == 0):
self._downloader.trouble(u'ERROR: no known formats available for video') raise ExtractorError(u'ERROR: no known formats available for video')
return
self._downloader.to_screen(u'[youporn] Links found: %d' % len(links)) self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))