w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[XHamsterIE] Extract SD and HD video

Browse source
This commit is contained in:
rzhxeo 2013-10-26 20:38:54 +02:00
parent 49a25557b0
commit 5d0c97541a
1 changed files with 37 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

52
youtube_dl/extractor/xhamster.py
View file

@ -36,21 +36,25 @@ class XHamsterIE(InfoExtractor):
}] }]
def _real_extract(self,url): def _real_extract(self,url):
def extract_video_url(webpage):
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0:
return compat_urllib_parse.unquote(mobj.group('file'))
else:
return mobj.group('server')+'/key='+mobj.group('file')
def is_hd(webpage):
return webpage.find('<div class=\'icon iconHD\'>') != -1
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
seo = mobj.group('seo') seo = mobj.group('seo')
mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo) mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
webpage = self._download_webpage(mrss_url, video_id) webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0:
video_url = compat_urllib_parse.unquote(mobj.group('file'))
else:
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title') webpage, u'title')
@ -76,14 +80,32 @@ class XHamsterIE(InfoExtractor):
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
return [{ video_url = extract_video_url(webpage)
'id': video_id, hd = is_hd(webpage)
'url': video_url, formats = [{
'ext': determine_ext(video_url), 'url': video_url,
'title': video_title, 'ext': determine_ext(video_url),
'format': 'hd' if hd else 'sd',
'format_id': 'hd' if hd else 'sd',
}]
if not hd:
webpage = self._download_webpage(mrss_url+'?hd', video_id)
if is_hd(webpage):
video_url = extract_video_url(webpage)
formats.append({
'url': video_url,
'ext': determine_ext(video_url),
'format': 'hd',
'format_id': 'hd',
})
return {
'id': video_id,
'title': video_title,
'formats': formats,
'description': video_description, 'description': video_description,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'uploader_id': video_uploader_id, 'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'age_limit': age_limit, 'age_limit': age_limit,
}] }