[einthusan] Fix extraction (closes #11416)

The old test URLs are no longer valid, so I replace them with the one
from #11416
This commit is contained in:
Yen Chi Hsuan 2017-02-12 20:53:55 +08:00
parent 459818e280
commit f8514630db
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
2 changed files with 75 additions and 45 deletions

View file

@ -3,6 +3,9 @@ version <unreleased>
Core Core
* TypeError is fixed with Python 2.7.13 on Windows (#11540, #12085) * TypeError is fixed with Python 2.7.13 on Windows (#11540, #12085)
Extractor
* [einthusan] Fix extraction (#11416)
version 2017.02.11 version 2017.02.11

View file

@ -1,67 +1,94 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import base64
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import (
compat_urlparse,
compat_str,
)
from ..utils import ( from ..utils import (
remove_start, extract_attributes,
sanitized_Request, ExtractorError,
get_elements_by_class,
urlencode_postdata,
) )
class EinthusanIE(InfoExtractor): class EinthusanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P<id>[0-9]+)' _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[0-9]+)'
_TESTS = [ _TEST = {
{ 'url': 'https://einthusan.tv/movie/watch/9097/',
'url': 'http://www.einthusan.com/movies/watch.php?id=2447', 'md5': 'ff0f7f2065031b8a2cf13a933731c035',
'md5': 'd71379996ff5b7f217eca034c34e3461', 'info_dict': {
'info_dict': { 'id': '9097',
'id': '2447', 'ext': 'mp4',
'ext': 'mp4', 'title': 'Ae Dil Hai Mushkil',
'title': 'Ek Villain', 'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:9d29fc91a7abadd4591fb862fa560d93', }
} }
},
{ # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
'url': 'http://www.einthusan.com/movies/watch.php?id=1671', def _decrypt(self, encrypted_data, video_id):
'md5': 'b16a6fd3c67c06eb7c79c8a8615f4213', return self._parse_json(base64.b64decode((
'info_dict': { encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
'id': '1671', ).encode('ascii')).decode('utf-8'), video_id)
'ext': 'mp4',
'title': 'Soodhu Kavvuum',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c',
}
},
]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
request = sanitized_Request(url) webpage = self._download_webpage(url, video_id)
request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
webpage = self._download_webpage(request, video_id)
title = self._html_search_regex( title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
r'<h1><a[^>]+class=["\']movie-title["\'][^>]*>(.+?)</a></h1>',
webpage, 'title')
video_id = self._search_regex( player_params = extract_attributes(self._search_regex(
r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id) r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
m3u8_url = self._download_webpage( page_id = self._html_search_regex(
'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/' '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
% video_id, video_id, headers={'Referer': url}) video_data = self._download_json(
formats = self._extract_m3u8_formats( 'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id,
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native') data=urlencode_postdata({
'xEvent': 'UIVideoPlayer.PingOutcome',
'xJson': json.dumps({
'EJOutcomes': player_params['data-ejpingables'],
'NativeHLS': False
}),
'arcVersion': 3,
'appVersion': 59,
'gorilla.csrf.Token': page_id,
}))['Data']
description = self._html_search_meta('description', webpage) if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
raise ExtractorError(
'Download rate reached. Please try again later.', expected=True)
ej_links = self._decrypt(video_data['EJLinks'], video_id)
formats = []
m3u8_url = ej_links.get('HLSLink')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
mp4_url = ej_links.get('MP4Link')
if mp4_url:
formats.append({
'url': mp4_url,
})
self._sort_formats(formats)
description = get_elements_by_class('synopsis', webpage)[0]
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'''<a class="movie-cover-wrapper".*?><img src=["'](.*?)["'].*?/></a>''', r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
webpage, "thumbnail url", fatal=False) webpage, 'thumbnail url', fatal=False, group='url')
if thumbnail is not None: if thumbnail is not None:
thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..')) thumbnail = compat_urlparse.urljoin(url, thumbnail)
return { return {
'id': video_id, 'id': video_id,