diff options
Diffstat (limited to 'hypervideo_dl/extractor/dailymotion.py')
| -rw-r--r-- | hypervideo_dl/extractor/dailymotion.py | 36 |
1 files changed, 20 insertions, 16 deletions
diff --git a/hypervideo_dl/extractor/dailymotion.py b/hypervideo_dl/extractor/dailymotion.py index 9cb5618..2a44718 100644 --- a/hypervideo_dl/extractor/dailymotion.py +++ b/hypervideo_dl/extractor/dailymotion.py @@ -1,6 +1,3 @@ -# coding: utf-8 -from __future__ import unicode_literals - import functools import json import re @@ -8,13 +5,15 @@ import re from .common import InfoExtractor from ..compat import compat_HTTPError from ..utils import ( + ExtractorError, + OnDemandPagedList, age_restricted, clean_html, - ExtractorError, int_or_none, - OnDemandPagedList, + traverse_obj, try_get, unescapeHTML, + unsmuggle_url, urlencode_postdata, ) @@ -100,6 +99,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): [/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))? ''' IE_NAME = 'dailymotion' + _EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1'] _TESTS = [{ 'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news', 'md5': '074b95bdee76b9e3654137aee9c79dfe', @@ -209,20 +209,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor): } xid''' - @staticmethod - def _extract_urls(webpage): - urls = [] - # Look for embedded Dailymotion player + @classmethod + def _extract_embed_urls(cls, url, webpage): # https://developer.dailymotion.com/player#player-parameters - for mobj in re.finditer( - r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage): - urls.append(unescapeHTML(mobj.group('url'))) + yield from super()._extract_embed_urls(url, webpage) for mobj in re.finditer( r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage): - urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id')) - return urls + yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id') def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url) video_id, playlist_id = self._match_valid_url(url).groups() if playlist_id: @@ -255,7 +251,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): metadata = self._download_json( 'https://www.dailymotion.com/player/metadata/video/' + xid, xid, 'Downloading metadata JSON', - query={'app': 'com.dailymotion.neon'}) + query=traverse_obj(smuggled_data, 'query') or {'app': 'com.dailymotion.neon'}) error = metadata.get('error') if error: @@ -297,7 +293,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor): f['url'] = f['url'].split('#')[0] if not f.get('fps') and f['format_id'].endswith('@60'): f['fps'] = 60 - self._sort_formats(formats) subtitles = {} subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {} @@ -378,6 +373,15 @@ class DailymotionPlaylistIE(DailymotionPlaylistBaseIE): }] _OBJECT_TYPE = 'collection' + @classmethod + def _extract_embed_urls(cls, url, webpage): + # Look for embedded Dailymotion playlist player (#3822) + for mobj in re.finditer( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', + webpage): + for p in re.findall(r'list\[\]=/playlist/([^/]+)/', unescapeHTML(mobj.group('url'))): + yield '//dailymotion.com/playlist/%s' % p + class DailymotionUserIE(DailymotionPlaylistBaseIE): IE_NAME = 'dailymotion:user' |