Browse Source

Move WorldStarHipHop into its own file

rtmp_test
Philipp Hagemeister 11 years ago
parent
commit
250f557872
2 changed files with 45 additions and 39 deletions
  1. +1
    -39
      youtube_dl/InfoExtractors.py
  2. +44
    -0
      youtube_dl/extractor/worldstarhiphop.py

+ 1
- 39
youtube_dl/InfoExtractors.py View File

@ -44,6 +44,7 @@ from .extractor.stanfordoc import StanfordOpenClassroomIE
from .extractor.steam import SteamIE
from .extractor.ted import TEDIE
from .extractor.vimeo import VimeoIE
from .extractor.worldstarhiphop import WorldStarHipHopIE
from .extractor.xnxx import XNXXIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
@ -258,45 +259,6 @@ class UstreamIE(InfoExtractor):
}
return info
class WorldStarHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
IE_NAME = u'WorldStarHipHop'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage_src = self._download_webpage(url, video_id)
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
webpage_src, u'video URL')
if 'mp4' in video_url:
ext = 'mp4'
else:
ext = 'flv'
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
webpage_src, u'thumbnail', fatal=False)
if not thumbnail:
_title = r"""candytitles.*>(.*)</span>"""
mobj = re.search(_title, webpage_src)
if mobj is not None:
video_title = mobj.group(1)
results = [{
'id': video_id,
'url' : video_url,
'title' : video_title,
'thumbnail' : thumbnail,
'ext' : ext,
}]
return results
class RBMARadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'


+ 44
- 0
youtube_dl/extractor/worldstarhiphop.py View File

@ -0,0 +1,44 @@
import re
from .common import InfoExtractor
class WorldStarHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
IE_NAME = u'WorldStarHipHop'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage_src = self._download_webpage(url, video_id)
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
webpage_src, u'video URL')
if 'mp4' in video_url:
ext = 'mp4'
else:
ext = 'flv'
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
webpage_src, u'thumbnail', fatal=False)
if not thumbnail:
_title = r"""candytitles.*>(.*)</span>"""
mobj = re.search(_title, webpage_src)
if mobj is not None:
video_title = mobj.group(1)
results = [{
'id': video_id,
'url' : video_url,
'title' : video_title,
'thumbnail' : thumbnail,
'ext' : ext,
}]
return results

Loading…
Cancel
Save