From 4e4db743e76387991b9f20613caec2c5ec38473a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 28 Apr 2019 00:42:55 +0100 Subject: [PATCH] [cinemax] Add new extractor --- youtube_dl/extractor/cinemax.py | 29 ++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/hbo.py | 44 +++++++++++++++++------------- 3 files changed, 55 insertions(+), 19 deletions(-) create mode 100644 youtube_dl/extractor/cinemax.py diff --git a/youtube_dl/extractor/cinemax.py b/youtube_dl/extractor/cinemax.py new file mode 100644 index 000000000..7f89d33de --- /dev/null +++ b/youtube_dl/extractor/cinemax.py @@ -0,0 +1,29 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .hbo import HBOBaseIE + + +class CinemaxIE(HBOBaseIE): + _VALID_URL = r'https?://(?:www\.)?cinemax\.com/(?P[^/]+/video/[0-9a-z-]+-(?P\d+))' + _TESTS = [{ + 'url': 'https://www.cinemax.com/warrior/video/s1-ep-1-recap-20126903', + 'md5': '82e0734bba8aa7ef526c9dd00cf35a05', + 'info_dict': { + 'id': '20126903', + 'ext': 'mp4', + 'title': 'S1 Ep 1: Recap', + }, + 'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'], + }, { + 'url': 'https://www.cinemax.com/warrior/video/s1-ep-1-recap-20126903.embed', + 'only_matching': True, + }] + + def _real_extract(self, url): + path, video_id = re.match(self._VALID_URL, url).groups() + info = self._extract_info('https://www.cinemax.com/%s.xml' % path, video_id) + info['id'] = video_id + return info diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 676ad3f7d..487ef2778 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -194,6 +194,7 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE +from .cinemax import CinemaxIE from .ciscolive import ( CiscoLiveSessionIE, CiscoLiveSearchIE, diff --git a/youtube_dl/extractor/hbo.py b/youtube_dl/extractor/hbo.py index 44440233d..68df748f5 100644 --- a/youtube_dl/extractor/hbo.py +++ b/youtube_dl/extractor/hbo.py @@ -13,19 +13,7 @@ from ..utils import ( ) -class HBOIE(InfoExtractor): - IE_NAME = 'hbo' - _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?:video|embed)(?:/[^/]+)*/(?P[^/?#]+)' - _TEST = { - 'url': 'https://www.hbo.com/video/game-of-thrones/seasons/season-8/videos/trailer', - 'md5': '8126210656f433c452a21367f9ad85b3', - 'info_dict': { - 'id': '22113301', - 'ext': 'mp4', - 'title': 'Game of Thrones - Trailer', - }, - 'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'], - } +class HBOBaseIE(InfoExtractor): _FORMATS_INFO = { 'pro7': { 'width': 1280, @@ -65,12 +53,8 @@ class HBOIE(InfoExtractor): }, } - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - location_path = self._parse_json(self._html_search_regex( - r'data-state="({.+?})"', webpage, 'state'), display_id)['video']['locationUrl'] - video_data = self._download_xml(urljoin(url, location_path), display_id) + def _extract_info(self, url, display_id): + video_data = self._download_xml(url, display_id) video_id = xpath_text(video_data, 'id', fatal=True) episode_title = title = xpath_text(video_data, 'title', fatal=True) series = xpath_text(video_data, 'program') @@ -167,3 +151,25 @@ class HBOIE(InfoExtractor): 'thumbnails': thumbnails, 'subtitles': subtitles, } + + +class HBOIE(HBOBaseIE): + IE_NAME = 'hbo' + _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?:video|embed)(?:/[^/]+)*/(?P[^/?#]+)' + _TEST = { + 'url': 'https://www.hbo.com/video/game-of-thrones/seasons/season-8/videos/trailer', + 'md5': '8126210656f433c452a21367f9ad85b3', + 'info_dict': { + 'id': '22113301', + 'ext': 'mp4', + 'title': 'Game of Thrones - Trailer', + }, + 'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'], + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + location_path = self._parse_json(self._html_search_regex( + r'data-state="({.+?})"', webpage, 'state'), display_id)['video']['locationUrl'] + return self._extract_info(urljoin(url, location_path), display_id) -- 2.22.2