diff options
author | peugeot <peugeot@psa.fr> | 2014-08-30 20:54:38 +0200 |
---|---|---|
committer | peugeot <peugeot@psa.fr> | 2014-08-30 20:54:38 +0200 |
commit | 12c82cf9cb59e97186b96fea76a15b52a0a9bb37 (patch) | |
tree | 074ce0aa9a5cf1f66e06632d2040c9d922c2cc57 | |
parent | 676e3ecf245f230411c9d534b0a4e918c01f5d86 (diff) |
add support for view count
-rw-r--r-- | youtube_dl/extractor/vporn.py | 10 |
1 files changed, 7 insertions, 3 deletions
diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index bdbd7543d..0d182b650 100644 --- a/youtube_dl/extractor/vporn.py +++ b/youtube_dl/extractor/vporn.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import int_or_none class VpornIE(InfoExtractor): _VALID_URL = r'http?://(?:www\.)?vporn\.com/[a-z]+/(?P<title_dash>[a-z-]+)/(?P<id>\d+)/?' @@ -30,15 +31,18 @@ class VpornIE(InfoExtractor): description = self._html_search_regex(r'<div class="description_txt">(.*?)</div>', webpage, 'description') thumbnail = 'http://www.vporn.com' + self._html_search_regex(r'flashvars.imageUrl = "(.*?)"', webpage, 'description') - mobj = re.search( - r'<span class="f_right">duration (?P<minutes>\d+) min (?P<seconds>\d+) sec </span>', webpage) + mobj = re.search(r'<span class="f_right">duration (?P<minutes>\d+) min (?P<seconds>\d+) sec </span>', webpage) duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + mobj = re.search(r'<span>((?P<thousands>\d+),)?(?P<units>\d+) VIEWS</span>', webpage) + view_count = int(mobj.group('thousands')) * 1000 + int(mobj.group('units')) if mobj else None + return { 'id': video_id, 'url': video_url, 'thumbnail': thumbnail, 'title': title, 'description': description, - 'duration': duration, + 'duration': int_or_none(duration), + 'view_count': int_or_none(view_count), } |