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

   1 #! -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import hashlib
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     compat_urllib_request,
  11     compat_urlparse,
  12 )
  13
  14
  15 class FC2IE(InfoExtractor):
  16     _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?content/(?P<id>[^/]+)'
  17     IE_NAME = 'fc2'
  18     _TEST = {
  19         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
  20         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
  21         'info_dict': {
  22             'id': '20121103kUan1KHs',
  23             'ext': 'flv',
  24             'title': 'Boxing again with Puff',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         self._downloader.cookiejar.clear_session_cookies()  # must clear
  34
  35         title = self._og_search_title(webpage)
  36         thumbnail = self._og_search_thumbnail(webpage)
  37         refer = url.replace('/content/', '/a/content/')
  38
  39         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
  40
  41         info_url = (
  42             "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&".
  43             format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E')))
  44
  45         info_webpage = self._download_webpage(
  46             info_url, video_id, note='Downloading info page')
  47         info = compat_urlparse.parse_qs(info_webpage)
  48
  49         if 'err_code' in info:
  50             raise ExtractorError('Error code: %s' % info['err_code'][0])
  51
  52         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
  53         title_info = info.get('title')
  54         if title_info:
  55             title = title_info[0]
  56
  57         return {
  58             'id': video_id,
  59             'title': title,
  60             'url': video_url,
  61             'ext': 'flv',
  62             'thumbnail': thumbnail,
  63         }