aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-09-20 11:16:12 +0600
committerSergey M․ <dstftw@gmail.com>2015-09-20 11:16:12 +0600
commit6c91a5a7f5408cf666f3ee40b53c0d9e42521b88 (patch)
tree73ca9d5ea3ad0bee3f5ef550064b8f3940dd07e2 /youtube_dl
parent749b09616de652b0f78958503175b91a626b1275 (diff)
[extractor/generic] Fix following redirect in Refresh HTTP header on python 2
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/generic.py20
1 files changed, 20 insertions, 0 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index ec748ed9f..8881a8a23 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import os
import re
+import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
@@ -231,6 +232,22 @@ class GenericIE(InfoExtractor):
}
},
{
+ # redirect in Refresh HTTP header
+ 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
+ 'info_dict': {
+ 'id': 'pO8h3EaFRdo',
+ 'ext': 'mp4',
+ 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
+ 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
+ 'upload_date': '20150917',
+ 'uploader_id': 'brtvofficial',
+ 'uploader': 'Boiler Room',
+ },
+ 'params': {
+ 'skip_download': False,
+ },
+ },
+ {
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
'info_dict': {
@@ -1808,6 +1825,9 @@ class GenericIE(InfoExtractor):
# Look also in Refresh HTTP header
refresh_header = head_response.headers.get('Refresh')
if refresh_header:
+ # In python 2 response HTTP headers are bytestrings
+ if sys.version_info < (3, 0) and isinstance(refresh_header, str):
+ refresh_header = refresh_header.decode('iso-8859-1')
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))