_ Git - youtube-dl/blob - youtube_dl/extractor/zaq1.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     unified_strdate,
   7     int_or_none
   8 )
   9
  10
  11 class Zaq1IE(InfoExtractor):
  12     _VALID_URL = r'http://(?:www\.)?zaq1\.pl/video/(?P<id>[^/?#&]+)'
  13     _TESTS = [{
  14         'url': 'http://zaq1.pl/video/xev0e',
  15         'md5': '24a5eb3f052e604ae597c4d0d19b351e',
  16         'info_dict': {
  17             'id': 'xev0e',
  18             'title': 'DJ NA WESELE. TANIEC Z FIGURAMI.węgrów/sokołów podlaski/siedlce/mińsk mazowiecki/warszawa',
  19             'ext': 'mp4',
  20             'duration': 511,
  21             'uploader': 'Anonim',
  22             'upload_date': '20170330',
  23         }
  24     }, {
  25         'url': 'http://zaq1.pl/video/x80nc',
  26         'md5': '1245973520adc78139928a820959d9c5',
  27         'info_dict': {
  28             'id': 'x80nc',
  29             'title': 'DIY Inspiration Challenge #86 | koraliki | gwiazdka na choinkę z koralików i drutu',
  30             'ext': 'mp4',
  31             'duration': 438,
  32             'uploader': 'Anonim',
  33             'upload_date': '20170404',
  34         }
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(url, video_id)
  41
  42         title = self._html_search_regex(
  43             r'(?s)<h1>\s*<span.+class="watch-title".+title="([^"]+)">\1\s*</span>\s*</h1>', webpage, 'title')
  44
  45         div = self._search_regex(r'(?s)(?P<div><div.+id=(["\'])video_player\2.+</div>)', webpage, 'video url', group='div')
  46         video_url = self._search_regex(r'data-video-url="(http[^"]+)"', div, 'video url')
  47
  48         ext = self._search_regex(r'data-file-extension="([^"]+)"', div, 'ext', None, False)
  49         duration = int_or_none(self._search_regex(r'data-duration="([^"]+)"', div, 'duration', None, False))
  50         thumbnail = self._search_regex(r'data-photo-url="([^"]+)"', div, 'thumbnail', None, False)
  51
  52         upload_date = unified_strdate(self._search_regex(r'<strong\s+class="watch-time-text">\s*Opublikowany\s+([0-9]{4}-[0-9]{2}-[0-9]{2})', webpage, 'upload date'))
  53         uploader = self._search_regex(r'<div\s+id="watch7-user-header">.*Wideo dodał:\s*<a[^>]*>\s*([^<]+)\s*</a>', webpage, 'uploader')
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': [{
  59                 'url': video_url,
  60                 'ext': ext,
  61                 'http_headers': {'Referer': url},
  62             }],
  63             'thumbnail': thumbnail,
  64             'uploader': uploader,
  65             'upload_date': upload_date,
  66             'duration': duration,
  67         }