diff options
Diffstat (limited to 'youtube_dl/extractor/dailymail.py')
| -rw-r--r-- | youtube_dl/extractor/dailymail.py | 29 |
1 files changed, 24 insertions, 5 deletions
diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py index 98c835bf1..af3978035 100644 --- a/youtube_dl/extractor/dailymail.py +++ b/youtube_dl/extractor/dailymail.py @@ -1,17 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, determine_protocol, + try_get, unescapeHTML, ) class DailyMailIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html', 'md5': 'f6129624562251f628296c3a9ffde124', 'info_dict': { @@ -20,7 +24,16 @@ class DailyMailIE(InfoExtractor): 'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'', 'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84', } - } + }, { + 'url': 'http://www.dailymail.co.uk/embed/video/1295863.html', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)', + webpage) def _real_extract(self, url): video_id = self._match_id(url) @@ -28,8 +41,14 @@ class DailyMailIE(InfoExtractor): video_data = self._parse_json(self._search_regex( r"data-opts='({.+?})'", webpage, 'video data'), video_id) title = unescapeHTML(video_data['title']) - video_sources = self._download_json(video_data.get( - 'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id) + + sources_url = (try_get( + video_data, + (lambda x: x['plugins']['sources']['url'], + lambda x: x['sources']['url']), compat_str) or + 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id) + + video_sources = self._download_json(sources_url, video_id) formats = [] for rendition in video_sources['renditions']: |