X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fgeneric.py;h=2c8fcf5ae5df24a1dedc5e461feb5ac2300688a6;hb=cf519235455f312ac45e1d9829018eb5ecbec628;hp=019bbe6e9f7ab7fcec303a44f1e51cc7fba36fa9;hpb=427023a1e6f2bb45a61b2bbfd56f845ee0c0ffee;p=youtube-dl.git
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 019bbe6e9..2c8fcf5ae 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -1,3 +1,5 @@
+# encoding: utf-8
+
import os
import re
@@ -6,24 +8,51 @@ from ..utils import (
compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
+ compat_urlparse,
ExtractorError,
+ smuggle_url,
+ unescapeHTML,
)
+from .brightcove import BrightcoveIE
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
+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'6e15c93721d7ec9e9ca3fdbf07982cfd',
+ u'info_dict': {
+ u"uploader": u"www.hodiho.fr",
+ u"title": u"R\u00e9gis plante sa Jeep"
+ }
+ },
+ # embedded vimeo video
+ {
+ u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references',
+ u'file': u'22444065.mp4',
+ u'md5': u'2903896e23df39722c33f015af0666e2',
+ u'info_dict': {
+ u'title': u'ACCU 2011: Move Semantics,Perfect Forwarding, and Rvalue references- Scott Meyers- 13/04/2011',
+ u"uploader_id": u"skillsmatter",
+ u"uploader": u"Skills Matter",
+ }
+ },
+ # bandcamp page with custom domain
+ {
+ u'url': u'http://bronyrock.com/track/the-pony-mash',
+ u'file': u'3235767654.mp3',
+ u'info_dict': {
+ u'title': u'The Pony Mash',
+ u'uploader': u'M_Pallante',
+ },
+ u'skip': u'There is a limit of 200 free downloads / month for the test song',
+ },
+ ]
def report_download_webpage(self, video_id):
"""Report webpage download."""
@@ -92,8 +121,18 @@ 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)]
+ parsed_url = compat_urlparse.urlparse(url)
+ if not parsed_url.scheme:
+ self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+ return self.url_result('http://' + 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:
@@ -101,9 +140,37 @@ class GenericIE(InfoExtractor):
except ValueError:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
- raise ExtractorError(u'Invalid URL: %s' % url)
+ raise ExtractorError(u'Failed to download URL: %s' % url)
self.report_extraction(video_id)
+ # Look for BrightCove:
+ m_brightcove = re.search(r'', 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')
+
+ # Look for embedded Vimeo player
+ mobj = re.search(
+ r'