administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 07:01:45 +00:00
Code Issues Projects Releases Wiki Activity

[laola1tv] Improve (Closes #8478)

Browse Source
This commit is contained in:
Sergey M․ 2016-02-14 23:40:26 +06:00
parent d9da74bc06
commit 9dcefb23a1
1 changed files with 57 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
youtube_dl/extractor/laola1tv.py
View File

@ -1,31 +1,35 @@
# -*- coding: utf-8 -*- # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..compat import (
compat_urllib_parse,
compat_urlparse, compat_urlparse,
)
from ..utils import (
ExtractorError, ExtractorError,
sanitized_Request, sanitized_Request,
xpath_element,
xpath_text,
unified_strdate, unified_strdate,
urlencode_postdata, urlencode_postdata,
xpath_element,
xpath_text,
) )
class Laola1TvIE(InfoExtractor): class Laola1TvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<slug>[\w-]+)' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/[^/]+/(?P<slug>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
'info_dict': { 'info_dict': {
'categories': ['Eishockey'],
'ext': 'flv',
'id': '227883', 'id': '227883',
'is_live': False, 'display_id': 'straubing-tigers-koelner-haie',
'ext': 'flv',
'title': 'Straubing Tigers - Kölner Haie', 'title': 'Straubing Tigers - Kölner Haie',
'upload_date': '20140912', 'upload_date': '20140912',
'is_live': False,
'categories': ['Eishockey'],
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -33,12 +37,13 @@ class Laola1TvIE(InfoExtractor):
}, { }, {
'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie', 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
'info_dict': { 'info_dict': {
'categories': ['Eishockey'],
'ext': 'flv',
'id': '464602', 'id': '464602',
'is_live': False, 'display_id': 'straubing-tigers-koelner-haie',
'ext': 'flv',
'title': 'Straubing Tigers - Kölner Haie', 'title': 'Straubing Tigers - Kölner Haie',
'upload_date': '20160129', 'upload_date': '20160129',
'is_live': False,
'categories': ['Eishockey'],
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -47,67 +52,74 @@ class Laola1TvIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('slug')
lang = mobj.group('lang') lang = mobj.group('lang')
portal = mobj.group('portal') portal = mobj.group('portal')
webpage = self._download_webpage(url, mobj.group('slug')) webpage = self._download_webpage(url, display_id)
iframe_url = self._search_regex( iframe_url = self._search_regex(
r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"', r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
webpage, 'iframe URL') webpage, 'iframe url')
video_id = self._search_regex( video_id = self._search_regex(
r'videoid=(\d+)', iframe_url, 'video ID') r'videoid=(\d+)', iframe_url, 'video id')
iframe = self._download_webpage(compat_urlparse.urljoin( iframe = self._download_webpage(compat_urlparse.urljoin(
url, iframe_url), video_id, note='Downloading iframe') url, iframe_url), display_id, 'Downloading iframe')
partner_id = self._search_regex( partner_id = self._search_regex(
r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner ID') r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
iframe, 'partner id', group='partner_id')
xml_url = ('http://www.laola1.tv/server/hd_video.php?' + hd_doc = self._download_xml(
'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % ( 'http://www.laola1.tv/server/hd_video.php?%s'
video_id, partner_id, portal, lang)) % compat_urllib_parse.urlencode({
hd_doc = self._download_xml(xml_url, video_id) 'play': video_id,
'partner': partner_id,
'portal': portal,
'lang': lang,
'v5ident': '',
}), display_id)
_v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k) _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
title = _v('title', fatal=True) title = _v('title', fatal=True)
categories = _v('meta_sports') req = sanitized_Request(
if categories: 'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
categories = categories.split(',') compat_urllib_parse.urlencode({
'videoId': video_id,
time_date = _v('time_date') 'target': '2',
time_start = _v('time_start') 'label': 'laola1tv',
upload_date = None 'area': _v('area'),
if time_date and time_start: }),
upload_date = unified_strdate(time_date + ' ' + time_start) urlencode_postdata(
json_url = ('https://club.laola1.tv/sp/laola1/api/v3/user/session' +
'/premium/player/stream-access?videoId=%s&target=2' +
'&label=laola1tv&area=%s') % (video_id, _v('area'))
req = sanitized_Request(json_url, urlencode_postdata(
dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))) dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
token_url = self._download_json(req, video_id)['data']['stream-access'][0] token_url = self._download_json(req, display_id)['data']['stream-access'][0]
token_doc = self._download_xml( token_doc = self._download_xml(token_url, display_id, 'Downloading token')
token_url, video_id, note='Downloading token')
token_attrib = xpath_element(token_doc, './/token').attrib token_attrib = xpath_element(token_doc, './/token').attrib
token_auth = token_attrib['auth'] token_auth = token_attrib['auth']
if token_auth in ('blocked', 'restricted'): if token_auth in ('blocked', 'restricted', 'error'):
raise ExtractorError( raise ExtractorError(
'Token error: %s' % token_attrib['comment'], expected=True) 'Token error: %s' % token_attrib['comment'], expected=True)
video_url = '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth) formats = self._extract_f4m_formats(
'%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
video_id, f4m_id='hds')
categories_str = _v('meta_sports')
categories = categories_str.split(',') if categories_str else []
return { return {
'categories': categories,
'formats': self._extract_f4m_formats(
video_url, video_id, f4m_id='hds'),
'id': video_id, 'id': video_id,
'is_live': _v('islive') == 'true', 'display_id': display_id,
'title': title, 'title': title,
'upload_date': upload_date, 'upload_date': unified_strdate(_v('time_date')),
'uploader': _v('meta_organisation'), 'uploader': _v('meta_organisation'),
'categories': categories,
'is_live': _v('islive') == 'true',
'formats': formats,
} }