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_parse,
   9     compat_urllib_request,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     encode_dict,
  14     ExtractorError,
  15     sanitized_Request,
  16 )
  17
  18
  19 class FC2IE(InfoExtractor):
  20     _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
  21     IE_NAME = 'fc2'
  22     _NETRC_MACHINE = 'fc2'
  23     _TESTS = [{
  24         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
  25         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
  26         'info_dict': {
  27             'id': '20121103kUan1KHs',
  28             'ext': 'flv',
  29             'title': 'Boxing again with Puff',
  30         },
  31     }, {
  32         'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
  33         'info_dict': {
  34             'id': '20150125cEva0hDn',
  35             'ext': 'mp4',
  36         },
  37         'params': {
  38             'username': 'ytdl@yt-dl.org',
  39             'password': '(snip)',
  40         },
  41         'skip': 'requires actual password',
  42     }, {
  43         'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
  44         'only_matching': True,
  45     }]
  46
  47     def _login(self):
  48         (username, password) = self._get_login_info()
  49         if username is None or password is None:
  50             return False
  51
  52         # Log in
  53         login_form_strs = {
  54             'email': username,
  55             'password': password,
  56             'done': 'video',
  57             'Submit': ' Login ',
  58         }
  59
  60         login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
  61         request = sanitized_Request(
  62             'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
  63
  64         login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
  65         if 'mode=redirect&login=done' not in login_results:
  66             self.report_warning('unable to log in: bad username or password')
  67             return False
  68
  69         # this is also needed
  70         login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done')
  71         self._download_webpage(
  72             login_redir, None, note='Login redirect', errnote='Login redirect failed')
  73
  74         return True
  75
  76     def _real_extract(self, url):
  77         video_id = self._match_id(url)
  78         self._login()
  79         webpage = self._download_webpage(url, video_id)
  80         self._downloader.cookiejar.clear_session_cookies()  # must clear
  81         self._login()
  82
  83         title = self._og_search_title(webpage)
  84         thumbnail = self._og_search_thumbnail(webpage)
  85         refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
  86
  87         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
  88
  89         info_url = (
  90             '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&'.
  91             format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E')))
  92
  93         info_webpage = self._download_webpage(
  94             info_url, video_id, note='Downloading info page')
  95         info = compat_urlparse.parse_qs(info_webpage)
  96
  97         if 'err_code' in info:
  98             # most of the time we can still download wideo even if err_code is 403 or 602
  99             self.report_warning(
 100                 'Error code was: %s... but still trying' % info['err_code'][0])
 101
 102         if 'filepath' not in info:
 103             raise ExtractorError('Cannot download file. Are you logged in?')
 104
 105         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
 106         title_info = info.get('title')
 107         if title_info:
 108             title = title_info[0]
 109
 110         return {
 111             'id': video_id,
 112             'title': title,
 113             'url': video_url,
 114             'ext': 'flv',
 115             'thumbnail': thumbnail,
 116         }