From 0838239e8e454c55903f3d69560cf53e25ce69f4 Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Sat, 24 Aug 2013 22:49:52 +0200
Subject: [generic] Support double slash URLs (Fixes #1309)

---
 youtube_dl/extractor/generic.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'youtube_dl/extractor/generic.py')

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index da016f7ee..ccbbdd255 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -7,12 +7,14 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
+    compat_urllib_parse_urlparse,
     compat_urllib_request,
 
     ExtractorError,
 )
 from .brightcove import BrightcoveIE
 
+
 class GenericIE(InfoExtractor):
     IE_DESC = u'Generic downloader that works on some sites'
     _VALID_URL = r'.*'
@@ -23,7 +25,7 @@ class GenericIE(InfoExtractor):
             u'file': u'13601338388002.mp4',
             u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89',
             u'info_dict': {
-                u"uploader": u"www.hodiho.fr", 
+                u"uploader": u"www.hodiho.fr",
                 u"title": u"R\u00e9gis plante sa Jeep"
             }
         },
@@ -161,6 +163,8 @@ class GenericIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         video_url = compat_urllib_parse.unquote(mobj.group(1))
+        if video_url.startswith('//'):
+            video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
         video_id = os.path.basename(video_url)
 
         # here's a fun little line of code for you:
-- 
cgit v1.2.3


From 9585f890f8c0eff70eb874c7962dc30baea1049c Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Sat, 24 Aug 2013 22:56:37 +0200
Subject: [generic] add support for relative URLs (Fixes #1308)

---
 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 ccbbdd255..8488dca05 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -165,6 +165,8 @@ class GenericIE(InfoExtractor):
         video_url = compat_urllib_parse.unquote(mobj.group(1))
         if video_url.startswith('//'):
             video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
+        if '://' not in video_url:
+            video_url = url + ('' if url.endswith('/') else '/') + video_url
         video_id = os.path.basename(video_url)
 
         # here's a fun little line of code for you:
-- 
cgit v1.2.3


From 627a91a9a827b48270d3f5e288404388946f0733 Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Mon, 26 Aug 2013 21:29:31 +0200
Subject: [generic] small typo

---
 youtube_dl/extractor/generic.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'youtube_dl/extractor/generic.py')

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 8488dca05..d034a11bb 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -126,7 +126,7 @@ class GenericIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         self.report_extraction(video_id)
-        # Look for BrigthCove:
+        # 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.')
-- 
cgit v1.2.3


From ae3531adf926998d42d1fb52453491c85e33b5f0 Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Wed, 28 Aug 2013 12:04:44 +0200
Subject: [generic] Fix URL concatenation

When the url is something like http://example.org/foo/bar?x=y  and the added is file/video.mp4 , we want http://example.org/foo/file/video.mp4
Fixes #1268.
---
 youtube_dl/extractor/generic.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'youtube_dl/extractor/generic.py')

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index d034a11bb..bfc9bff49 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -166,7 +166,12 @@ class GenericIE(InfoExtractor):
         if video_url.startswith('//'):
             video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
         if '://' not in video_url:
-            video_url = url + ('' if url.endswith('/') else '/') + video_url
+            up = compat_urllib_parse_urlparse(url)
+            if video_url.startswith('/'):
+                video_url = up.scheme + '://' + up.netloc + video_url
+            else:  # relative path
+                video_url = (up.scheme + '://' + up.netloc +
+                             up.path.rpartition('/')[0] + '/' + video_url)
         video_id = os.path.basename(video_url)
 
         # here's a fun little line of code for you:
-- 
cgit v1.2.3


From a5caba1eb02665cdc982d6be4a933aafd79243de Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Wed, 28 Aug 2013 12:47:27 +0200
Subject: [generic] simply use urljoin

---
 youtube_dl/extractor/generic.py | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'youtube_dl/extractor/generic.py')

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index bfc9bff49..dc4dea4ad 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -7,8 +7,8 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_parse_urlparse,
     compat_urllib_request,
+    compat_urlparse,
 
     ExtractorError,
 )
@@ -163,15 +163,7 @@ class GenericIE(InfoExtractor):
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         video_url = compat_urllib_parse.unquote(mobj.group(1))
-        if video_url.startswith('//'):
-            video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
-        if '://' not in video_url:
-            up = compat_urllib_parse_urlparse(url)
-            if video_url.startswith('/'):
-                video_url = up.scheme + '://' + up.netloc + video_url
-            else:  # relative path
-                video_url = (up.scheme + '://' + up.netloc +
-                             up.path.rpartition('/')[0] + '/' + video_url)
+        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:
-- 
cgit v1.2.3


From 08e291b54d8aaa34300c02e70ff86aaa36820a62 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
 <jaime.marquinez.ferrandiz@gmail.com>
Date: Thu, 5 Sep 2013 18:02:17 +0200
Subject: [generic] Recognize html5 video in the format '<video src=".+?"' and
 only unquote the url when extracting the id (fixes #1372)

---
 youtube_dl/extractor/generic.py | 6 +++---
 1 file changed, 3 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 dc4dea4ad..de7379a92 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -153,7 +153,7 @@ class GenericIE(InfoExtractor):
                 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)
+            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
@@ -162,9 +162,9 @@ class GenericIE(InfoExtractor):
         if mobj.group(1) is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
-        video_url = compat_urllib_parse.unquote(mobj.group(1))
+        video_url = mobj.group(1)
         video_url = compat_urlparse.urljoin(url, video_url)
-        video_id = os.path.basename(video_url)
+        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
         # here's a fun little line of code for you:
         video_extension = os.path.splitext(video_id)[1][1:]
-- 
cgit v1.2.3


From a7130543fa0368175740f5fa173ef920671db866 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
 <jaime.marquinez.ferrandiz@gmail.com>
Date: Fri, 6 Sep 2013 18:39:35 +0200
Subject: [generic] If the url doesn't specify the protocol, then try to
 extract prepending 'http://'

---
 youtube_dl/extractor/generic.py | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'youtube_dl/extractor/generic.py')

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index de7379a92..f92e61fea 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -109,6 +109,11 @@ class GenericIE(InfoExtractor):
         return new_url
 
     def _real_extract(self, 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:
-- 
cgit v1.2.3