_ Git - youtube-dl/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_parse,
  11     compat_urllib_request,
  12     compat_urlparse,
  13 )
  14
  15
  16 class FC2IE(InfoExtractor):
  17     _VALID_URL = r'^http://video\.fc2\.com/((?P<lang>[^/]+)/)?(a/)?content/(?P<id>[^/]+)'
  18     IE_NAME = 'fc2'
  19     _NETRC_MACHINE = 'fc2'
  20     _TEST = {
  21         'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
  22         'md5': 'a6ebe8ebe0396518689d963774a54eb7',
  23         'info_dict': {
  24             'id': '20121103kUan1KHs',
  25             'ext': 'flv',
  26             'title': 'Boxing again with Puff',
  27         },
  28     }
  29
  30     #def _real_initialize(self):
  31     #    self._login()
  32
  33     def _login(self):
  34         (username, password) = self._get_login_info()
  35         if (username is None) or (password is None):
  36            self.to_screen('unable to log in: will be downloading in non authorized mode') # report_warning
  37            return False
  38
  39         # Log in
  40         login_form_strs = {
  41             'email':    username,
  42             'password': password,
  43             'done':     'video',
  44             'Submit':   ' Login ',
  45         }
  46
  47         # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
  48         # chokes on unicode
  49         login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
  50         login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
  51         request    = compat_urllib_request.Request(
  52             'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
  53
  54         login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
  55         if 'mode=redirect&login=done' not in login_results:
  56             self.to_screen('unable to log in: bad username or password') # report_warning
  57             return False
  58
  59         # this is also needed
  60         login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
  61         redir_res   = self._download_webpage(login_redir, None, note='Login redirect', errnote='Something is not right')
  62
  63         return True
  64
  65     def _real_extract(self, url):
  66         mobj = re.match(self._VALID_URL, url)
  67         video_id = mobj.group('id')
  68
  69         webpage = self._download_webpage(url, video_id)
  70         self._downloader.cookiejar.clear_session_cookies()  # must clear
  71         self._login()
  72
  73         title = self._og_search_title(webpage)
  74         thumbnail = self._og_search_thumbnail(webpage)
  75
  76         refer = (url if '/a/content/' in url else url.replace('/content/', '/a/content/'));
  77         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
  78
  79         info_url = (
  80             "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&".
  81             format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E')))
  82
  83         info_webpage = self._download_webpage(
  84             info_url, video_id, note='Downloading info page')
  85         info = compat_urlparse.parse_qs(info_webpage)
  86
  87         if 'err_code' in info:
  88             #raise ExtractorError('Error code: %s' % info['err_code'][0])
  89             # most of the time we can still download wideo even if err_code is 403 or 602
  90             self.to_screen('Error code was: %s... but still trying' % info['err_code'][0]) # report_warning
  91
  92         if 'filepath' not in info:
  93             raise ExtractorError('Cannot download file. Are you logged?')
  94
  95         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
  96         title_info = info.get('title')
  97         if title_info:
  98             title = title_info[0]
  99
 100         return {
 101             'id': video_id,
 102             'title': title,
 103             'url': video_url,
 104             'ext': 'flv',
 105             'thumbnail': thumbnail,
 106         }