youtube_dl/extractor/funimation.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 from .common import InfoExtractor
   4 from ..compat import compat_HTTPError
   5 from ..utils import (
   6     encode_dict,
   7     sanitized_Request,
   8     ExtractorError,
   9     urlencode_postdata
  10 )
  11 import re
  12
  13
  14 class FunimationIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/.+[^ ]/videos/official/(?P<id>[^?]+)'
  16
  17     _TEST = {
  18         'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
  19         'info_dict': {
  20             'id': 'AIRENG0001',
  21             'title': 'Air - 1 - Breeze ',
  22             'ext': 'mp4',
  23             'thumbnail': 'http://www.funimation.com/admin/uploads/default/recap_thumbnails/7555590/home_spotlight/AIR0001.jpg',
  24             'description': 'Travelling puppeteer Yukito arrives in a small town where he hopes to earn money through the magic of his puppets. When a young girl named Misuzu lures him to her home with the promise of food, his life changes forever. ',
  25         }
  26     }
  27
  28     def _login(self):
  29         (username, password) = self._get_login_info()
  30         if username is None:
  31             return
  32         login_url = 'http://www.funimation.com/login'
  33         data = urlencode_postdata(encode_dict({
  34             'email_field': username,
  35             'password_field': password,
  36         }))
  37         login_request = sanitized_Request(login_url, data, headers={
  38             'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
  39             'Content-Type': 'application/x-www-form-urlencoded'
  40         })
  41         try:
  42             login = self._download_webpage(
  43                 login_request, None, 'Logging in as %s' % username)
  44         except ExtractorError as e:
  45             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  46                 raise ExtractorError('Funimation is not available in your region.', expected=True)
  47             raise
  48         if re.search(r'<meta property="og:url" content="http://www.funimation.com/login"/>', login) is not None:
  49             raise ExtractorError('Unable to login, wrong username or password.', expected=True)
  50
  51     def _real_initialize(self):
  52         self._login()
  53
  54     def _real_extract(self, url):
  55         mobj = re.match(self._VALID_URL, url)
  56         video_id = mobj.group('id')
  57         try:
  58             webpage = self._download_webpage(url, video_id)
  59         except ExtractorError as e:
  60             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  61                 raise ExtractorError('Funimation is not available in your region.', expected=True)
  62             raise
  63         if re.search(r'"sdUrl":"http', webpage) is None:
  64                 raise ExtractorError('You are not logged-in or the stream requires subscription.', expected=True)
  65
  66         m3u8 = self._search_regex(r'".+Url":"(.+?m3u8)"', webpage, 'm3u8') + self._search_regex(r'"authToken":"(.+?)"', webpage, 'm3u8')
  67         formats = self._extract_m3u8_formats(m3u8.replace('\\', ''), video_id, ext='mp4', entry_protocol='m3u8_native')
  68
  69         video_show = self._search_regex(r'"artist":"(.+?)"', webpage, 'video_show')
  70         video_track = self._search_regex(r'"videoNumber":"(\d+).0"', webpage, 'video_track')
  71         video_title = self._search_regex(r'"title":"({0}.+?)"'.format(video_track), webpage, 'video_title')
  72         video_id = self._search_regex(r'"FUNImationID":"(.+?)"', webpage, 'video_id')
  73
  74         return {
  75             'id': video_id,
  76             'title': video_show + ' - ' + video_title + ' ',
  77             'formats': formats,
  78             'thumbnail': self._og_search_thumbnail(webpage),
  79             'description': self._og_search_description(webpage)
  80         }