[escapist] Detect IP blocking and use another UA (Fixes #5069)

This commit is contained in:
Philipp Hagemeister 2015-02-26 09:19:26 +01:00
parent 5c340b0387
commit 63a562f95e

View File

@ -3,6 +3,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
@ -12,6 +13,7 @@
class EscapistIE(InfoExtractor): class EscapistIE(InfoExtractor):
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])' _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
_USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'
_TEST = { _TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate', 'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1', 'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
@ -28,7 +30,9 @@ class EscapistIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(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( uploader_id = self._html_search_regex(
r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'", r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
@ -54,9 +58,11 @@ def _real_extract(self, url):
formats = [] formats = []
ad_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(
cfgurl, video_id, cfg_req, video_id,
'Downloading ' + name + ' configuration', 'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration', 'Unable to download ' + name + ' configuration',
transform_source=js_to_json) transform_source=js_to_json)
@ -74,6 +80,9 @@ def _add_format(name, cfgurl, quality):
'url': p['url'], 'url': p['url'],
'format_id': name, 'format_id': name,
'quality': quality, '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 @@ def _add_format(name, cfgurl, quality):
pass # That's fine, we'll just use normal quality pass # That's fine, we'll just use normal quality
self._sort_formats(formats) 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 = { res = {
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,