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