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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     clean_html,
   9     int_or_none,
  10     js_to_json,
  11     parse_iso8601,
  12 )
  13
  14
  15 class NetzkinoIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/(?P<category>[^/]+)/(?P<id>[^/]+)'
  17
  18     _TEST = {
  19         'url': 'http://www.netzkino.de/#!/scifikino/rakete-zum-mond',
  20         'md5': '92a3f8b76f8d7220acce5377ea5d4873',
  21         'info_dict': {
  22             'id': 'rakete-zum-mond',
  23             'ext': 'mp4',
  24             'title': 'Rakete zum Mond (Endstation Mond, Destination Moon)',
  25             'comments': 'mincount:3',
  26             'description': 'md5:1eddeacc7e62d5a25a2d1a7290c64a28',
  27             'upload_date': '20120813',
  28             'thumbnail': 're:https?://.*\.jpg$',
  29             'timestamp': 1344858571,
  30             'age_limit': 12,
  31         },
  32         'params': {
  33             'skip_download': 'Download only works from Germany',
  34         }
  35     }
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         category_id = mobj.group('category')
  40         video_id = mobj.group('id')
  41
  42         api_url = 'http://api.netzkino.de.simplecache.net/capi-2.0a/categories/%s.json?d=www' % category_id
  43         api_info = self._download_json(api_url, video_id)
  44         info = next(
  45             p for p in api_info['posts'] if p['slug'] == video_id)
  46         custom_fields = info['custom_fields']
  47
  48         production_js = self._download_webpage(
  49             'http://www.netzkino.de/beta/dist/production.min.js', video_id,
  50             note='Downloading player code')
  51         avo_js = self._search_regex(
  52             r'window\.avoCore\s*=.*?urlTemplate:\s*(\{.*?"\})',
  53             production_js, 'URL templates')
  54         templates = self._parse_json(
  55             avo_js, video_id, transform_source=js_to_json)
  56
  57         suffix = {
  58             'hds': '.mp4/manifest.f4m',
  59             'hls': '.mp4/master.m3u8',
  60             'pmd': '.mp4',
  61         }
  62         film_fn = custom_fields['Streaming'][0]
  63         formats = [{
  64             'format_id': key,
  65             'ext': 'mp4',
  66             'url': tpl.replace('{}', film_fn) + suffix[key],
  67         } for key, tpl in templates.items()]
  68         self._sort_formats(formats)
  69
  70         comments = [{
  71             'timestamp': parse_iso8601(c.get('date'), delimiter=' '),
  72             'id': c['id'],
  73             'author': c['name'],
  74             'html': c['content'],
  75             'parent': 'root' if c.get('parent', 0) == 0 else c['parent'],
  76         } for c in info.get('comments', [])]
  77
  78         return {
  79             'id': video_id,
  80             'formats': formats,
  81             'comments': comments,
  82             'title': info['title'],
  83             'age_limit': int_or_none(custom_fields.get('FSK')[0]),
  84             'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
  85             'description': clean_html(info.get('content')),
  86             'thumbnail': info.get('thumbnail'),
  87             'playlist_title': api_info.get('title'),
  88             'playlist_id': category_id,
  89         }