Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/zippcast.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     str_to_int,
   9 )
  10
  11
  12 class ZippCastIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?zippcast\.com/(?:video/|videoview\.php\?.*\bvplay=)(?P<id>[0-9a-zA-Z]+)'
  14     _TESTS = [{
  15         # m3u8, hq direct link
  16         'url': 'http://www.zippcast.com/video/c9cfd5c7e44dbc29c81',
  17         'md5': '5ea0263b5606866c4d6cda0fc5e8c6b6',
  18         'info_dict': {
  19             'id': 'c9cfd5c7e44dbc29c81',
  20             'ext': 'mp4',
  21             'title': '[Vinesauce] Vinny - Digital Space Traveler',
  22             'description': 'Muted on youtube, but now uploaded in it\'s original form.',
  23             'thumbnail': 're:^https?://.*\.jpg$',
  24             'uploader': 'vinesauce',
  25             'view_count': int,
  26             'categories': ['Entertainment'],
  27             'tags': list,
  28         },
  29     }, {
  30         # f4m, lq ipod direct link
  31         'url': 'http://www.zippcast.com/video/b79c0a233e9c6581775',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.zippcast.com/videoview.php?vplay=c9cfd5c7e44dbc29c81&auto=no',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         webpage = self._download_webpage(
  42             'http://www.zippcast.com/video/%s' % video_id, video_id)
  43
  44         formats = []
  45         video_url = self._search_regex(
  46             r'<source[^>]+src=(["\'])(?P<url>.+?)\1', webpage,
  47             'video url', default=None, group='url')
  48         if video_url:
  49             formats.append({
  50                 'url': video_url,
  51                 'format_id': 'http',
  52                 'preference': 0,  # direct link is almost always of worse quality
  53             })
  54         src_url = self._search_regex(
  55             r'src\s*:\s*(?:escape\()?(["\'])(?P<url>http://.+?)\1',
  56             webpage, 'src', default=None, group='url')
  57         ext = determine_ext(src_url)
  58         if ext == 'm3u8':
  59             formats.extend(self._extract_m3u8_formats(
  60                 src_url, video_id, 'mp4', entry_protocol='m3u8_native',
  61                 m3u8_id='hls', fatal=False))
  62         elif ext == 'f4m':
  63             formats.extend(self._extract_f4m_formats(
  64                 src_url, video_id, f4m_id='hds', fatal=False))
  65         self._sort_formats(formats)
  66
  67         title = self._og_search_title(webpage)
  68         description = self._og_search_description(webpage) or self._html_search_meta(
  69             'description', webpage)
  70         uploader = self._search_regex(
  71             r'<a[^>]+href="https?://[^/]+/profile/[^>]+>([^<]+)</a>',
  72             webpage, 'uploader', fatal=False)
  73         thumbnail = self._og_search_thumbnail(webpage)
  74         view_count = str_to_int(self._search_regex(
  75             r'>([\d,.]+) views!', webpage, 'view count', fatal=False))
  76
  77         categories = re.findall(
  78             r'<a[^>]+href="https?://[^/]+/categories/[^"]+">([^<]+),?<',
  79             webpage)
  80         tags = re.findall(
  81             r'<a[^>]+href="https?://[^/]+/search/tags/[^"]+">([^<]+),?<',
  82             webpage)
  83
  84         return {
  85             'id': video_id,
  86             'title': title,
  87             'description': description,
  88             'thumbnail': thumbnail,
  89             'uploader': uploader,
  90             'view_count': view_count,
  91             'categories': categories,
  92             'tags': tags,
  93             'formats': formats,
  94         }