[tube8] Extract duration and modernize

This commit is contained in:
Sergey M․ 2016-01-20 20:07:32 +06:00
parent 27b83249c9
commit 7dde358adc

View file

@ -14,25 +14,23 @@
class Tube8IE(InfoExtractor): class Tube8IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
_TESTS = [ _TESTS = [{
{ 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', 'md5': '65e20c48e6abff62ed0c3965fff13a39',
'md5': '44bf12b98313827dd52d35b8706a4ea0', 'info_dict': {
'info_dict': { 'id': '229795',
'id': '229795', 'display_id': 'kasia-music-video',
'display_id': 'kasia-music-video', 'ext': 'mp4',
'ext': 'mp4', 'description': 'hot teen Kasia grinding',
'description': 'hot teen Kasia grinding', 'uploader': 'unknown',
'uploader': 'unknown', 'title': 'Kasia music video',
'title': 'Kasia music video', 'age_limit': 18,
'age_limit': 18, 'duration': 230,
} }
}, },{
{ 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', 'only_matching': True,
'only_matching': True, }]
},
]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -75,19 +73,18 @@ def _real_extract(self, url):
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'<span class="username">\s*(.+?)\s*<', r'<span class="username">\s*(.+?)\s*<',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
duration = int_or_none(flashvars.get('video_duration'))
like_count = int_or_none(self._html_search_regex( like_count = int_or_none(self._search_regex(
r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False)) r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
dislike_count = int_or_none(self._html_search_regex( dislike_count = int_or_none(self._search_regex(
r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
view_count = self._html_search_regex( view_count = str_to_int(self._search_regex(
r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False) r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
if view_count: webpage, 'view count', fatal=False))
view_count = str_to_int(view_count) comment_count = str_to_int(self._search_regex(
comment_count = self._html_search_regex( r'<span id="allCommentsCount">(\d+)</span>',
r'<span id="allCommentsCount">(\d+)</span>', webpage, 'comment count', fatal=False) webpage, 'comment count', fatal=False))
if comment_count:
comment_count = str_to_int(comment_count)
return { return {
'id': video_id, 'id': video_id,
@ -96,6 +93,7 @@ def _real_extract(self, url):
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'uploader': uploader, 'uploader': uploader,
'duration': duration,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count, 'like_count': like_count,
'dislike_count': dislike_count, 'dislike_count': dislike_count,