youtube_dl/extractor/videopress.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     determine_ext,
   9     float_or_none,
  10     int_or_none,
  11     parse_age_limit,
  12     qualities,
  13     random_birthday,
  14     unified_timestamp,
  15     urljoin,
  16 )
  17
  18
  19 class VideoPressIE(InfoExtractor):
  20     _ID_REGEX = r'[\da-zA-Z]{8}'
  21     _PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
  22     _VALID_URL = r'https?://%s(?P<id>%s)' % (_PATH_REGEX, _ID_REGEX)
  23     _TESTS = [{
  24         'url': 'https://videopress.com/embed/kUJmAcSf',
  25         'md5': '706956a6c875873d51010921310e4bc6',
  26         'info_dict': {
  27             'id': 'kUJmAcSf',
  28             'ext': 'mp4',
  29             'title': 'VideoPress Demo',
  30             'thumbnail': r're:^https?://.*\.jpg',
  31             'duration': 634.6,
  32             'timestamp': 1434983935,
  33             'upload_date': '20150622',
  34             'age_limit': 0,
  35         },
  36     }, {
  37         # 17+, requires birth_* params
  38         'url': 'https://videopress.com/embed/iH3gstfZ',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://video.wordpress.com/embed/kUJmAcSf',
  42         'only_matching': True,
  43     }]
  44
  45     @staticmethod
  46     def _extract_urls(webpage):
  47         return re.findall(
  48             r'<iframe[^>]+src=["\']((?:https?://)?%s%s)' % (VideoPressIE._PATH_REGEX, VideoPressIE._ID_REGEX),
  49             webpage)
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         query = random_birthday('birth_year', 'birth_month', 'birth_day')
  55         query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
  56         video = self._download_json(
  57             'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
  58             video_id, query=query)
  59
  60         title = video['title']
  61
  62         file_url_base = video.get('file_url_base') or {}
  63         base_url = file_url_base.get('https') or file_url_base.get('http')
  64
  65         QUALITIES = ('std', 'dvd', 'hd')
  66         quality = qualities(QUALITIES)
  67
  68         formats = []
  69         for format_id, f in (video.get('files') or {}).items():
  70             if not isinstance(f, dict):
  71                 continue
  72             for ext, path in f.items():
  73                 if ext in ('mp4', 'ogg'):
  74                     formats.append({
  75                         'url': urljoin(base_url, path),
  76                         'format_id': '%s-%s' % (format_id, ext),
  77                         'ext': determine_ext(path, ext),
  78                         'quality': quality(format_id),
  79                     })
  80         original_url = video.get('original')
  81         if original_url:
  82             formats.append({
  83                 'url': original_url,
  84                 'format_id': 'original',
  85                 'quality': len(QUALITIES),
  86                 'width': int_or_none(video.get('width')),
  87                 'height': int_or_none(video.get('height')),
  88             })
  89         self._sort_formats(formats)
  90
  91         return {
  92             'id': video_id,
  93             'title': title,
  94             'description': video.get('description'),
  95             'thumbnail': video.get('poster'),
  96             'duration': float_or_none(video.get('duration'), 1000),
  97             'timestamp': unified_timestamp(video.get('upload_date')),
  98             'age_limit': parse_age_limit(video.get('rating')),
  99             'formats': formats,
 100         }