projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
5c340b0
)
[escapist] Detect IP blocking and use another UA (Fixes #5069)
author
Philipp Hagemeister
<phihag@phihag.de>
Thu, 26 Feb 2015 08:19:26 +0000
(09:19 +0100)
committer
Philipp Hagemeister
<phihag@phihag.de>
Thu, 26 Feb 2015 08:19:26 +0000
(09:19 +0100)
youtube_dl/extractor/escapist.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/escapist.py
b/youtube_dl/extractor/escapist.py
index b45c1dbd07650d9717408591c7b20077bf62475e..80e9084f41ffd751ed407cbd9b79138fd4627140 100644
(file)
--- a/
youtube_dl/extractor/escapist.py
+++ b/
youtube_dl/extractor/escapist.py
@@
-3,6
+3,7
@@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
+ compat_urllib_request,
)
from ..utils import (
ExtractorError,
)
from ..utils import (
ExtractorError,
@@
-12,6
+13,7
@@
from ..utils import (
class EscapistIE(InfoExtractor):
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
class EscapistIE(InfoExtractor):
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+ _USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'
_TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
_TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
@@
-28,7
+30,9
@@
class EscapistIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ webpage_req = compat_urllib_request.Request(url)
+ webpage_req.add_header('User-Agent', self._USER_AGENT)
+ webpage = self._download_webpage(webpage_req, video_id)
uploader_id = self._html_search_regex(
r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
uploader_id = self._html_search_regex(
r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
@@
-54,9
+58,11
@@
class EscapistIE(InfoExtractor):
formats = []
ad_formats = []
formats = []
ad_formats = []
- def _add_format(name, cfgurl, quality):
+ def _add_format(name, cfg_url, quality):
+ cfg_req = compat_urllib_request.Request(cfg_url)
+ cfg_req.add_header('User-Agent', self._USER_AGENT)
config = self._download_json(
config = self._download_json(
- cfg
url
, video_id,
+ cfg
_req
, video_id,
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
transform_source=js_to_json)
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
transform_source=js_to_json)
@@
-74,6
+80,9
@@
class EscapistIE(InfoExtractor):
'url': p['url'],
'format_id': name,
'quality': quality,
'url': p['url'],
'format_id': name,
'quality': quality,
+ 'http_headers': {
+ 'User-Agent': self._USER_AGENT,
+ },
})
_add_format('normal', config_url, quality=0)
})
_add_format('normal', config_url, quality=0)
@@
-85,6
+94,9
@@
class EscapistIE(InfoExtractor):
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
+ if '/escapist/sales-marketing/' in formats[-1]['url']:
+ raise ExtractorError('This IP address has been blocked by The Escapist', expected=True)
+
res = {
'id': video_id,
'formats': formats,
res = {
'id': video_id,
'formats': formats,