diff options
author | Rogério Brito <rbrito@ime.usp.br> | 2017-03-08 22:53:10 -0300 |
---|---|---|
committer | Rogério Brito <rbrito@ime.usp.br> | 2017-03-08 22:53:10 -0300 |
commit | 2b4515201a54c38e34434ea2817d606be134a7c9 (patch) | |
tree | e7dcb445c80be55c497615529800ff74bb950c63 /youtube_dl/extractor/njpwworld.py | |
parent | 3cd33af594d34a8809318ebd0be4d606d212a7a0 (diff) | |
parent | 1d3fd83f473663fce3e0a10303473a38d80cc3d0 (diff) | |
download | youtube-dl-2b4515201a54c38e34434ea2817d606be134a7c9.zip youtube-dl-2b4515201a54c38e34434ea2817d606be134a7c9.tar.gz youtube-dl-2b4515201a54c38e34434ea2817d606be134a7c9.tar.bz2 |
Merge tag 'upstream/2017.03.07'
Upstream version 2017.03.07
Diffstat (limited to 'youtube_dl/extractor/njpwworld.py')
-rw-r--r-- | youtube_dl/extractor/njpwworld.py | 83 |
1 files changed, 83 insertions, 0 deletions
diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py new file mode 100644 index 0000000..f5e3f68 --- /dev/null +++ b/youtube_dl/extractor/njpwworld.py @@ -0,0 +1,83 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + get_element_by_class, + urlencode_postdata, +) + + +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): + self._login() + + 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, + m3u8_entry_protocol='m3u8_native', + preference=2 if 'hq' in kind else 1) + formats.extend(entries[0]['formats']) + + self._sort_formats(formats) + + 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, + } |