From a4eb9578af3ef0c0b4a3f73020743e1efe3c6c09 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 21 Apr 2014 06:18:04 +0200 Subject: [PATCH] [yahoo] Add support for movies (Fixes #2780) --- youtube_dl/extractor/yahoo.py | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 4671f49ed..393f6ffbe 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -14,8 +14,8 @@ from ..utils import ( class YahooIE(InfoExtractor): - IE_DESC = 'Yahoo screen' - _VALID_URL = r'https?://screen\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html' + IE_DESC = 'Yahoo screen and movies' + _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -37,6 +37,16 @@ class YahooIE(InfoExtractor): 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, }, + { + 'url': 'https://movies.yahoo.com/video/world-loves-spider-man-190819223.html', + 'md5': '410b7104aa9893b765bc22787a22f3d9', + 'info_dict': { + 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845', + 'ext': 'mp4', + 'title': 'The World Loves Spider-Man', + 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', + } + } ] def _real_extract(self, url): @@ -44,13 +54,20 @@ class YahooIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - items_json = self._search_regex(r'mediaItems: ({.*?})$', - webpage, 'items', flags=re.MULTILINE) - items = json.loads(items_json) - info = items['mediaItems']['query']['results']['mediaObj'][0] - # The 'meta' field is not always in the video webpage, we request it - # from another page - long_id = info['id'] + items_json = self._search_regex( + r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, + default=None) + if items_json is None: + long_id = self._search_regex( + r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', + webpage, 'content ID') + video_id = long_id + else: + items = json.loads(items_json) + info = items['mediaItems']['query']['results']['mediaObj'][0] + # The 'meta' field is not always in the video webpage, we request it + # from another page + long_id = info['id'] return self._get_info(long_id, video_id) def _get_info(self, long_id, video_id):