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     ExtractorError,
  14 )
  15
  16
  17 class FC2IE(InfoExtractor):
  18     _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
  19     IE_NAME = 'fc2'
  20     _NETRC_MACHINE = 'fc2'
  21     _TESTS = [{
  22         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
  23         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
  24         'info_dict': {
  25             'id': '20121103kUan1KHs',
  26             'ext': 'flv',
  27             'title': 'Boxing again with Puff',
  28         },
  29     }, {
  30         'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
  31         'info_dict': {
  32             'id': '20150125cEva0hDn',
  33             'ext': 'mp4',
  34         },
  35         'params': {
  36             'username': 'ytdl@yt-dl.org',
  37             'password': '(snip)',
  38             'skip': 'requires actual password'
  39         }
  40     }, {
  41         'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
  42         'only_matching': True,
  43     }]
  44
  45     def _login(self):
  46         (username, password) = self._get_login_info()
  47         if username is None or password is None:
  48             return False
  49
  50         # Log in
  51         login_form_strs = {
  52             'email': username,
  53             'password': password,
  54             'done': 'video',
  55             'Submit': ' Login ',
  56         }
  57
  58         # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
  59         # chokes on unicode
  60         login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
  61         login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
  62         request = compat_urllib_request.Request(
  63             'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
  64
  65         login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
  66         if 'mode=redirect&login=done' not in login_results:
  67             self.report_warning('unable to log in: bad username or password')
  68             return False
  69
  70         # this is also needed
  71         login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
  72         self._download_webpage(
  73             login_redir, None, note='Login redirect', errnote='Login redirect failed')
  74
  75         return True
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79         self._login()
  80         webpage = self._download_webpage(url, video_id)
  81         self._downloader.cookiejar.clear_session_cookies()  # must clear
  82         self._login()
  83
  84         title = self._og_search_title(webpage)
  85         thumbnail = self._og_search_thumbnail(webpage)
  86         refer = url.replace('/content/', '/a/content/')
  87
  88         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
  89
  90         info_url = (
  91             "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&".
  92             format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E')))
  93
  94         info_webpage = self._download_webpage(
  95             info_url, video_id, note='Downloading info page')
  96         info = compat_urlparse.parse_qs(info_webpage)
  97
  98         if 'err_code' in info:
  99             # most of the time we can still download wideo even if err_code is 403 or 602
 100             self.report_warning(
 101                 'Error code was: %s... but still trying' % info['err_code'][0])
 102
 103         if 'filepath' not in info:
 104             raise ExtractorError('Cannot download file. Are you logged in?')
 105
 106         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
 107         title_info = info.get('title')
 108         if title_info:
 109             title = title_info[0]
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'url': video_url,
 115             'ext': 'flv',
 116             'thumbnail': thumbnail,
 117         }