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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     parse_duration,
   9     unified_strdate,
  10 )
  11
  12
  13 class CamWithHerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P<id>\w+)'
  15
  16     _TESTS = [{
  17         'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=',
  18         'info_dict': {
  19             'id': '5644',
  20             'ext': 'flv',
  21             'title': 'Periscope Tease',
  22             'description': 'In the clouds teasing on periscope to my favorite song',
  23             'duration': 240,
  24             'view_count': int,
  25             'comment_count': int,
  26             'uploader': 'MileenaK',
  27             'upload_date': '20160322',
  28         },
  29         'params': {
  30             'skip_download': True,
  31         }
  32     }, {
  33         'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv',
  40         'only_matching': True,
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45
  46         webpage = self._download_webpage(url, video_id)
  47
  48         flv_id = self._html_search_regex(
  49             r'<a[^>]+href=["\']/download/\?v=(\d+)', webpage, 'video id')
  50
  51         # Video URL construction algorithm is reverse-engineered from cwhplayer.swf
  52         rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % (
  53             ('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id)
  54
  55         title = self._html_search_regex(
  56             r'<div[^>]+style="float:left"[^>]*>\s*<h2>(.+?)</h2>', webpage, 'title')
  57         description = self._html_search_regex(
  58             r'>Description:</span>(.+?)</div>', webpage, 'description', default=None)
  59
  60         runtime = self._search_regex(
  61             r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None)
  62         if runtime:
  63             runtime = re.sub(r'[\s-]', '', runtime)
  64         duration = parse_duration(runtime)
  65         view_count = int_or_none(self._search_regex(
  66             r'Views\s*:\s*(\d+)', webpage, 'view count', default=None))
  67         comment_count = int_or_none(self._search_regex(
  68             r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None))
  69
  70         uploader = self._search_regex(
  71             r'Added by\s*:\s*<a[^>]+>([^<]+)</a>', webpage, 'uploader', default=None)
  72         upload_date = unified_strdate(self._search_regex(
  73             r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None))
  74
  75         return {
  76             'id': flv_id,
  77             'url': rtmp_url,
  78             'ext': 'flv',
  79             'no_resume': True,
  80             'title': title,
  81             'description': description,
  82             'duration': duration,
  83             'view_count': view_count,
  84             'comment_count': comment_count,
  85             'uploader': uploader,
  86             'upload_date': upload_date,
  87         }