[laola1] add support for another extraction scenario(closes #11460)

This commit is contained in:
Remita Amine 2016-12-20 18:22:57 +01:00
parent 90352a8041
commit e029c43bd4

View file

@ -9,18 +9,41 @@ from ..utils import (
xpath_element, xpath_element,
xpath_text, xpath_text,
urljoin, urljoin,
update_url_query,
) )
class Laola1TvEmbedIE(InfoExtractor): class Laola1TvEmbedIE(InfoExtractor):
IE_NAME = 'laola1tv:embed'
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
_TEST = {
# flashvars.premium = "false";
'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
'info_dict': {
'id': '708065',
'ext': 'mp4',
'title': 'MA Long CHN - FAN Zhendong CHN',
'uploader': 'ITTF - International Table Tennis Federation',
'upload_date': '20161211',
},
}
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 = self._download_webpage(url, video_id)
flash_vars = self._search_regex( flash_vars = self._search_regex(
r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars') r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars')
get_flashvar = lambda x: self._search_regex(r'%s\s*:\s*"([^"]+)"' % x, flash_vars, x)
def get_flashvar(x, *args, **kwargs):
flash_var = self._search_regex(
r'%s\s*:\s*"([^"]+)"' % x,
flash_vars, x, default=None)
if not flash_var:
flash_var = self._search_regex([
r'flashvars\.%s\s*=\s*"([^"]+)"' % x,
r'%s\s*=\s*"([^"]+)"' % x],
webpage, x, *args, **kwargs)
return flash_var
hd_doc = self._download_xml( hd_doc = self._download_xml(
'http://www.laola1.tv/server/hd_video.php', video_id, query={ 'http://www.laola1.tv/server/hd_video.php', video_id, query={
@ -34,6 +57,15 @@ class Laola1TvEmbedIE(InfoExtractor):
_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)
token_url = None
premium = get_flashvar('premium', default=None)
if premium:
token_url = update_url_query(
_v('url', fatal=True), {
'timestamp': get_flashvar('timestamp'),
'auth': get_flashvar('auth'),
})
else:
data_abo = urlencode_postdata( data_abo = 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( token_url = self._download_json(
@ -44,6 +76,7 @@ class Laola1TvEmbedIE(InfoExtractor):
'label': _v('label'), 'label': _v('label'),
'area': _v('area'), 'area': _v('area'),
}, data=data_abo)['data']['stream-access'][0] }, data=data_abo)['data']['stream-access'][0]
token_doc = self._download_xml( token_doc = self._download_xml(
token_url, video_id, 'Downloading token', token_url, video_id, 'Downloading token',
headers=self.geo_verification_headers()) headers=self.geo_verification_headers())
@ -75,6 +108,7 @@ class Laola1TvEmbedIE(InfoExtractor):
class Laola1TvIE(InfoExtractor): class Laola1TvIE(InfoExtractor):
IE_NAME = 'laola1tv'
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
_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',