_ Git - youtube-dl/blob - youtube_dl/extractor/goshgay.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urlparse,
   9     str_to_int,
  10     ExtractorError,
  11 )
  12 import json
  13
  14
  15 class GoshgayIE(InfoExtractor):
  16     _VALID_URL = r'^(?:https?://)www.goshgay.com/video(?P<id>\d+?)($|/)'
  17     _TEST = {
  18         'url': 'http://www.goshgay.com/video4116282',
  19         'md5': '268b9f3c3229105c57859e166dd72b03',
  20         'info_dict': {
  21             'id': '4116282',
  22             'ext': 'flv',
  23             'title': 'md5:089833a4790b5e103285a07337f245bf',
  24             'thumbnail': 're:http://.*\.jpg',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')
  34
  35         player_config = self._search_regex(r'jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings',
  36                                            fatal=True, flags=re.S)
  37         player_vars = json.loads(player_config.replace("'", '"'))
  38         width = str_to_int(player_vars.get('width'))
  39         height = str_to_int(player_vars.get('height'))
  40         config_uri = player_vars.get('config')
  41
  42         if config_uri is None:
  43             raise ExtractorError('Missing config URI')
  44         node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
  45                                   errnote='Unable to download XML')
  46         if node is None:
  47             raise ExtractorError('Missing config XML')
  48         if node.tag != 'config':
  49             raise ExtractorError('Missing config attribute')
  50         fns = node.findall('file')
  51         imgs = node.findall('image')
  52         if len(fns) != 1:
  53             raise ExtractorError('Missing media URI')
  54         video_url = fns[0].text
  55         if len(imgs) < 1:
  56             thumbnail = None
  57         else:
  58             thumbnail = imgs[0].text
  59
  60         url_comp = compat_urlparse.urlparse(url)
  61         ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'title': title,
  67             'width': width,
  68             'height': height,
  69             'thumbnail': thumbnail,
  70             'http_referer': ref,
  71             'age_limit': 18,
  72         }