From 2dcf7d8f99604de9bdfa1b1e12a2bd5840d523d2 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Tue, 5 Nov 2013 02:08:02 +0100 Subject: [GenericIE] Also detect youtube if src url of iframe is embedded in ' instaed of " --- youtube_dl/extractor/generic.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2c8fcf5ae..b3fec8e86 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -160,9 +160,9 @@ class GenericIE(InfoExtractor): # Look for embedded YouTube player mobj = re.search( - r']+?src="(https?://(?:www\.)?youtube.com/embed/.+?)"', webpage) + r']+?src=(["\'])(?Phttps?://(?:www\.)?youtube.com/embed/.+?)\1', webpage) if mobj: - surl = unescapeHTML(mobj.group(1)) + surl = unescapeHTML(mobj.group(u'url')) return self.url_result(surl, 'Youtube') # Look for Bandcamp pages with custom domain -- cgit v1.2.3 From 9ee2b5f6f2a6e07ab901e47ede59eb5382ebb6ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 3 Nov 2013 19:14:53 +0100 Subject: tests: don't run the test if any of the extractors listed in the 'add_ie' field is marked as not working --- youtube_dl/extractor/generic.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index b3fec8e86..76d369273 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -33,6 +33,7 @@ class GenericIE(InfoExtractor): }, # embedded vimeo video { + u'add_ie': ['Vimeo'], u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references', u'file': u'22444065.mp4', u'md5': u'2903896e23df39722c33f015af0666e2', @@ -44,6 +45,7 @@ class GenericIE(InfoExtractor): }, # bandcamp page with custom domain { + u'add_ie': ['Bandcamp'], u'url': u'http://bronyrock.com/track/the-pony-mash', u'file': u'3235767654.mp3', u'info_dict': { -- cgit v1.2.3 From eeb165e674e07aaa798f69e15f16faa01bc8feaa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Wed, 6 Nov 2013 16:40:24 +0100 Subject: [brightcove] Add the extraction of the url from generic --- youtube_dl/extractor/generic.py | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 76d369273..04b7212f4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -54,6 +54,21 @@ class GenericIE(InfoExtractor): }, u'skip': u'There is a limit of 200 free downloads / month for the test song', }, + # embedded brightcove video + { + u'add_ie': ['Brightcove'], + u'url': u'http://www.scientificamerican.com/article.cfm?id=soap-bubble-physics', + u'info_dict': { + u'id': u'2365799484001', + u'ext': u'mp4', + u'title': u'Bubble Simulation', + u'description': u'A visualization from a new computer model of foam behavior.', + u'uploader': u'Scientific American', + }, + u'params': { + u'skip_download': True, + }, + }, ] def report_download_webpage(self, video_id): @@ -146,10 +161,9 @@ class GenericIE(InfoExtractor): self.report_extraction(video_id) # Look for BrightCove: - m_brightcove = re.search(r']+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?', webpage, re.DOTALL) - if m_brightcove is not None: + bc_url = BrightcoveIE._extract_brightcove_url(webpage) + if bc_url is not None: self.to_screen(u'Brightcove video detected.') - bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group()) return self.url_result(bc_url, 'Brightcove') # Look for embedded Vimeo player -- cgit v1.2.3 From dd5bcdc4c9cad0ee7e2d61343129ee1111048189 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 7 Nov 2013 21:06:48 +0100 Subject: [brightcove] Set the 'Referer' header if the url has the 'linkBaseUrl' parameter (fixes #1553) --- youtube_dl/extractor/generic.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'youtube_dl/extractor/generic.py') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 04b7212f4..c7552fddb 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -55,15 +55,17 @@ class GenericIE(InfoExtractor): u'skip': u'There is a limit of 200 free downloads / month for the test song', }, # embedded brightcove video + # it also tests brightcove videos that need to set the 'Referer' in the + # http requests { u'add_ie': ['Brightcove'], - u'url': u'http://www.scientificamerican.com/article.cfm?id=soap-bubble-physics', + u'url': u'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', u'info_dict': { - u'id': u'2365799484001', + u'id': u'2765128793001', u'ext': u'mp4', - u'title': u'Bubble Simulation', - u'description': u'A visualization from a new computer model of foam behavior.', - u'uploader': u'Scientific American', + u'title': u'Le cours de bourse : l’analyse technique', + u'description': u'md5:7e9ad046e968cb2d1114004aba466fd9', + u'uploader': u'BFM BUSINESS', }, u'params': { u'skip_download': True, -- cgit v1.2.3