diff options
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 56 |
1 files changed, 45 insertions, 11 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 20bc53330..dc4dea4ad 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1,3 +1,5 @@ +# encoding: utf-8 + import os import re @@ -6,23 +8,39 @@ from ..utils import ( compat_urllib_error, compat_urllib_parse, compat_urllib_request, + compat_urlparse, ExtractorError, ) +from .brightcove import BrightcoveIE + class GenericIE(InfoExtractor): IE_DESC = u'Generic downloader that works on some sites' _VALID_URL = r'.*' IE_NAME = u'generic' - _TEST = { - u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', - u'file': u'13601338388002.mp4', - u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89', - u'info_dict': { - u"uploader": u"www.hodiho.fr", - u"title": u"R\u00e9gis plante sa Jeep" - } - } + _TESTS = [ + { + u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', + u'file': u'13601338388002.mp4', + u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89', + u'info_dict': { + u"uploader": u"www.hodiho.fr", + u"title": u"R\u00e9gis plante sa Jeep" + } + }, + { + u'url': u'http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/', + u'file': u'2371591881001.mp4', + u'md5': u'9e80619e0a94663f0bdc849b4566af19', + u'note': u'Test Brightcove downloads and detection in GenericIE', + u'info_dict': { + u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”', + u'uploader': u'8TV', + u'description': u'md5:a950cc4285c43e44d763d036710cd9cd', + } + }, + ] def report_download_webpage(self, video_id): """Report webpage download.""" @@ -91,8 +109,13 @@ class GenericIE(InfoExtractor): return new_url def _real_extract(self, url): - new_url = self._test_redirect(url) - if new_url: return [self.url_result(new_url)] + try: + new_url = self._test_redirect(url) + if new_url: + return [self.url_result(new_url)] + except compat_urllib_error.HTTPError: + # This may be a stupid server that doesn't like HEAD, our UA, or so + pass video_id = url.split('/')[-1] try: @@ -103,6 +126,13 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) self.report_extraction(video_id) + # Look for BrightCove: + m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL) + if m_brightcove 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') + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: @@ -122,6 +152,9 @@ class GenericIE(InfoExtractor): if m_video_type is not None: mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) if mobj is None: + # HTML5 video + mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL) + if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) # It's possible that one of the regexes @@ -130,6 +163,7 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) video_url = compat_urllib_parse.unquote(mobj.group(1)) + video_url = compat_urlparse.urljoin(url, video_url) video_id = os.path.basename(video_url) # here's a fun little line of code for you: |