[crackle] Bypass geo restriction

This commit is contained in:
Sergey M․ 2018-03-24 01:49:50 +07:00
parent b9f5a41207
commit 7d34016fb0
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 109 additions and 83 deletions

View File

@ -4,20 +4,24 @@ from __future__ import unicode_literals, division
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import (
compat_str,
compat_HTTPError,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
float_or_none, float_or_none,
int_or_none, int_or_none,
parse_age_limit, parse_age_limit,
parse_duration, parse_duration,
ExtractorError
) )
class CrackleIE(InfoExtractor): class CrackleIE(InfoExtractor):
_GEO_COUNTRIES = ['US']
_VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)' _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
_TEST = { _TEST = {
# geo restricted to CA
'url': 'https://www.crackle.com/andromeda/2502343', 'url': 'https://www.crackle.com/andromeda/2502343',
'info_dict': { 'info_dict': {
'id': '2502343', 'id': '2502343',
@ -46,12 +50,32 @@ class CrackleIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
country_code = self._downloader.params.get('geo_bypass_country', None)
countries = [country_code] if country_code else (
'US', 'AU', 'CA', 'AS', 'FM', 'GU', 'MP', 'PR', 'PW', 'MH', 'VI')
last_e = None
for country in countries:
try:
media = self._download_json( media = self._download_json(
'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s' 'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s'
% (video_id, self._GEO_COUNTRIES[0]), video_id, query={ % (video_id, country), video_id,
'Downloading media JSON as %s' % country,
'Unable to download media JSON', query={
'disableProtocols': 'true', 'disableProtocols': 'true',
'format': 'json' 'format': 'json'
}) })
except ExtractorError as e:
# 401 means geo restriction, trying next country
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
last_e = e
continue
raise
media_urls = media.get('MediaURLs')
if not media_urls or not isinstance(media_urls, list):
continue
title = media['Title'] title = media['Title']
@ -136,3 +160,5 @@ class CrackleIE(InfoExtractor):
'subtitles': subtitles, 'subtitles': subtitles,
'formats': formats, 'formats': formats,
} }
raise last_e