[extractor/generic] Fix following redirect in Refresh HTTP header on python 2

This commit is contained in:
Sergey M․ 2015-09-20 11:16:12 +06:00
parent 749b09616d
commit 6c91a5a7f5

View file

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import os import os
import re import re
import sys
from .common import InfoExtractor from .common import InfoExtractor
from .youtube import YoutubeIE from .youtube import YoutubeIE
@ -230,6 +231,22 @@ class GenericIE(InfoExtractor):
'skip_download': False, 'skip_download': False,
} }
}, },
{
# 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', 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89', 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
@ -1808,6 +1825,9 @@ class GenericIE(InfoExtractor):
# Look also in Refresh HTTP header # Look also in Refresh HTTP header
refresh_header = head_response.headers.get('Refresh') refresh_header = head_response.headers.get('Refresh')
if refresh_header: 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) found = re.search(REDIRECT_REGEX, refresh_header)
if found: if found:
new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1))) new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))