[IPrima] Fix extractor (fixes #7617)

This commit is contained in:
pulpe 2016-02-06 21:23:41 +01:00
parent f326b5837a
commit f406c78785
1 changed files with 22 additions and 77 deletions

View File

@ -2,46 +2,30 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from random import random import time
from math import floor
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
remove_end,
sanitized_Request, sanitized_Request,
) )
class IPrimaIE(InfoExtractor): class IPrimaIE(InfoExtractor):
_WORKING = False _VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
_VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://play.iprima.cz/gondici-s-r-o-33',
'info_dict': {
'id': 'p136534',
'ext': 'mp4',
'title': 'Gondíci s. r. o. (34)',
'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
},
'params': {
'skip_download': True, # m3u8 download
},
}, {
'url': 'http://play.iprima.cz/particka/particka-92', 'url': 'http://play.iprima.cz/particka/particka-92',
'info_dict': {
'id': '39152',
'ext': 'flv',
'title': 'Partička (92)',
'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, {
'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
'info_dict': {
'id': '9718337',
'ext': 'flv',
'title': 'Tchibo Partička - Jarní móda',
'thumbnail': 're:^http:.*\.jpg$',
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, {
'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
'only_matching': True, 'only_matching': True,
}] }]
@ -51,62 +35,23 @@ class IPrimaIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage): video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
raise ExtractorError(
'%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
player_url = ( req = sanitized_Request('http://play.iprima.cz/prehravac/init?_infuse=1'
'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % '&_ts=%s&productId=%s' % (round(time.time()), 'p22201'))
(floor(random() * 1073741824), floor(random() * 1073741824))
)
req = sanitized_Request(player_url)
req.add_header('Referer', url) req.add_header('Referer', url)
playerpage = self._download_webpage(req, video_id) playerpage = self._download_webpage(req, video_id, note='Downloading player')
base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1]) m3u8_url = self._search_regex(r"'src': '([^']+\.m3u8)'", playerpage, 'm3u8 url')
zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO') formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
if zoneGEO != '0':
base_url = base_url.replace('token', 'token_' + zoneGEO)
formats = []
for format_id in ['lq', 'hq', 'hd']:
filename = self._html_search_regex(
r'"%s_id":(.+?),' % format_id, webpage, 'filename')
if filename == 'null':
continue
real_id = self._search_regex(
r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
filename, 'real video id')
if format_id == 'lq':
quality = 0
elif format_id == 'hq':
quality = 1
elif format_id == 'hd':
quality = 2
filename = 'hq/' + filename
formats.append({
'format_id': format_id,
'url': base_url,
'quality': quality,
'play_path': 'mp4:' + filename.replace('"', '')[:-4],
'rtmp_live': True,
'ext': 'flv',
})
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': real_id, 'id': video_id,
'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'), 'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats, 'formats': formats,
'description': self._search_regex( 'description': self._og_search_description(webpage),
r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
webpage, 'description', default=None),
} }