Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ringtv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class RingTVIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)'
   8     _TEST = {
   9         u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown",
  10         u"file": u"746619.mp4",
  11         u"md5": u"7c46b4057d22de32e0a539f017e64ad3",
  12         u"info_dict": {
  13             u"title": u"Canelo Alvarez talks about Mayweather showdown",
  14             u"description": u"Saul \\\"Canelo\\\" Alvarez spoke to the media about his Sept. 14 showdown with Floyd Mayweather after their kick-off presser in NYC. Canelo is motivated and confident that he will have the speed and gameplan to beat the pound-for-pound king."
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20         video_id = mobj.group(1).split('-')[0]
  21         webpage = self._download_webpage(url, video_id)
  22         title = self._search_regex(r'<title>(.+?)</title>',
  23                         webpage, 'video title').replace(' | RingTV','')
  24         description = self._search_regex(r'<div class="blurb">(.+?)</div>',
  25                         webpage, 'Description')
  26         final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id))
  27         thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id))
  28         ext = final_url.split('.')[-1]
  29         return [{
  30             'id'          : video_id,
  31             'url'         : final_url,
  32             'ext'         : ext,
  33             'title'       : title,
  34             'thumbnail'   : thumbnail_url,
  35             'description' : description,
  36         }]
  37