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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     int_or_none,
   9     qualities,
  10     determine_ext,
  11 )
  12
  13
  14 class SunPornoIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
  16     _TEST = {
  17         'url': 'http://www.sunporno.com/videos/807778/',
  18         'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
  19         'info_dict': {
  20             'id': '807778',
  21             'ext': 'flv',
  22             'title': 'md5:0a400058e8105d39e35c35e7c5184164',
  23             'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'duration': 302,
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         title = self._html_search_regex(
  36             r'<title>([^<]+)</title>', webpage, 'title')
  37         description = self._html_search_meta(
  38             'description', webpage, 'description')
  39         thumbnail = self._html_search_regex(
  40             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
  41
  42         duration = parse_duration(self._search_regex(
  43             r'itemprop="duration">\s*(\d+:\d+)\s*<',
  44             webpage, 'duration', fatal=False))
  45
  46         view_count = int_or_none(self._html_search_regex(
  47             r'class="views">\s*(\d+)\s*<',
  48             webpage, 'view count', fatal=False))
  49         comment_count = int_or_none(self._html_search_regex(
  50             r'(\d+)</b> Comments?',
  51             webpage, 'comment count', fatal=False))
  52
  53         formats = []
  54         quality = qualities(['mp4', 'flv'])
  55         for video_url in re.findall(r'<source src="([^"]+)"', webpage):
  56             video_ext = determine_ext(video_url)
  57             formats.append({
  58                 'url': video_url,
  59                 'format_id': video_ext,
  60                 'quality': quality(video_ext),
  61             })
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'description': description,
  68             'thumbnail': thumbnail,
  69             'duration': duration,
  70             'view_count': view_count,
  71             'comment_count': comment_count,
  72             'formats': formats,
  73             'age_limit': 18,
  74         }