Unverified Commit db182c63 authored by Yen Chi Hsuan's avatar Yen Chi Hsuan
Browse files

[njpwworld] Add new extractor (closes #11561)

parent eeb0a956
version <unreleased>
+ [njpwworld] Add new extractor (#11561)
version 2017.02.24.1
......@@ -637,6 +637,7 @@ from .ninecninemedia import (
from .ninegag import NineGagIE
from .ninenow import NineNowIE
from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
class NJPWWorldIE(InfoExtractor):
_VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
IE_DESC = '新日本プロレスワールド'
_NETRC_MACHINE = 'njpwworld'
_TEST = {
'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
'info_dict': {
'id': 's_series_00155_1_9',
'ext': 'mp4',
'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
'tags': list,
'params': {
'skip_download': True, # AES-encrypted m3u8
'skip': 'Requires login',
def _real_initialize(self):
def _login(self):
username, password = self._get_login_info()
# No authentication to be performed
if not username:
return True
webpage, urlh = self._download_webpage_handle(
'https://njpwworld.com/auth/login', None,
note='Logging in', errnote='Unable to login',
data=urlencode_postdata({'login_id': username, 'pw': password}))
# /auth/login will return 302 for successful logins
if urlh.geturl() == 'https://njpwworld.com/auth/login':
self.report_warning('unable to login')
return False
return True
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = []
for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
player_url = compat_urlparse.urljoin(url, player_url)
player_page = self._download_webpage(
player_url, video_id, note='Downloading player page')
entries = self._parse_html5_media_entries(
player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
preference=2 if 'hq' in kind else 1)
post_content = get_element_by_class('post-content', webpage)
tags = re.findall(
r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
) if post_content else None
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'tags': tags,
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment