Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/fc2.py

   1 #! -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import hashlib
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_request,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13 )
  14
  15
  16 class FC2IE(InfoExtractor):
  17     _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
  18     IE_NAME = 'fc2'
  19     _TEST = {
  20         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
  21         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
  22         'info_dict': {
  23             'id': '20121103kUan1KHs',
  24             'ext': 'flv',
  25             'title': 'Boxing again with Puff',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32         self._downloader.cookiejar.clear_session_cookies()  # must clear
  33
  34         title = self._og_search_title(webpage)
  35         thumbnail = self._og_search_thumbnail(webpage)
  36         refer = url.replace('/content/', '/a/content/')
  37
  38         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
  39
  40         info_url = (
  41             "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&".
  42             format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.', '%2E')))
  43
  44         info_webpage = self._download_webpage(
  45             info_url, video_id, note='Downloading info page')
  46         info = compat_urlparse.parse_qs(info_webpage)
  47
  48         if 'err_code' in info:
  49             raise ExtractorError('Error code: %s' % info['err_code'][0])
  50
  51         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
  52         title_info = info.get('title')
  53         if title_info:
  54             title = title_info[0]
  55
  56         return {
  57             'id': video_id,
  58             'title': title,
  59             'url': video_url,
  60             'ext': 'flv',
  61             'thumbnail': thumbnail,
  62         }