youtube_dl/extractor/clippit.py

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_iso8601,
   8     qualities,
   9 )
  10
  11 import re
  12
  13
  14 class ClippitIE(InfoExtractor):
  15
  16     _VALID_URL = r'https?://(?:www\.)?clippituser\.tv/c/(?P<id>[a-z]+)'
  17     _TEST = {
  18         'url': 'https://www.clippituser.tv/c/evmgm',
  19         'md5': '963ae7a59a2ec4572ab8bf2f2d2c5f09',
  20         'info_dict': {
  21             'id': 'evmgm',
  22             'ext': 'mp4',
  23             'title': 'Bye bye Brutus. #BattleBots  - Clippit',
  24             'uploader': 'lizllove',
  25             'uploader_url': 'https://www.clippituser.tv/p/lizllove',
  26             'timestamp': 1472183818,
  27             'upload_date': '20160826',
  28             'description': 'BattleBots | ABC',
  29             'thumbnail': r're:^https?://.*\.jpg$',
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         webpage = self._download_webpage(url, video_id)
  36
  37         title = self._html_search_regex(r'<title.*>(.+?)</title>', webpage, 'title')
  38
  39         FORMATS = ('sd', 'hd')
  40         quality = qualities(FORMATS)
  41         formats = []
  42         for format_id in FORMATS:
  43             url = self._html_search_regex(r'data-%s-file="(.+?)"' % format_id,
  44                                           webpage, 'url', fatal=False)
  45             if not url:
  46                 continue
  47             match = re.search(r'/(?P<height>\d+)\.mp4', url)
  48             formats.append({
  49                 'url': url,
  50                 'format_id': format_id,
  51                 'quality': quality(format_id),
  52                 'height': int(match.group('height')) if match else None,
  53             })
  54
  55         uploader = self._html_search_regex(r'class="username".*>\s+(.+?)\n',
  56                                            webpage, 'uploader', fatal=False)
  57         uploader_url = ('https://www.clippituser.tv/p/' + uploader
  58                         if uploader else None)
  59
  60         timestamp = self._html_search_regex(r'datetime="(.+?)"',
  61                                             webpage, 'date', fatal=False)
  62         thumbnail = self._html_search_regex(r'data-image="(.+?)"',
  63                                             webpage, 'thumbnail', fatal=False)
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'formats': formats,
  69             'uploader': uploader,
  70             'uploader_url': uploader_url,
  71             'timestamp': parse_iso8601(timestamp),
  72             'description': self._og_search_description(webpage),
  73             'thumbnail': thumbnail,
  74         }