From db182c63fb4a58974e425a56d235131fd9efc531 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sat, 25 Feb 2017 18:44:39 +0800 Subject: [PATCH] [njpwworld] Add new extractor (closes #11561) --- ChangeLog | 6 +++ youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/njpwworld.py | 83 ++++++++++++++++++++++++++++++ 3 files changed, 90 insertions(+) create mode 100644 youtube_dl/extractor/njpwworld.py diff --git a/ChangeLog b/ChangeLog index add8a6758..e0e1f52d0 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors ++ [njpwworld] Add new extractor (#11561) + + version 2017.02.24.1 Extractors diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 83a170fa7..703bc5d34 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -637,6 +637,7 @@ 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 diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py new file mode 100644 index 000000000..f5e3f6815 --- /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[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']+href="(/player[^"]+)".+?]+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']+class="tag-[^"]+">]*>([^<]+)', post_content + ) if post_content else None + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'formats': formats, + 'tags': tags, + }