From 92bf0bcdf847682cee9f66a5cef4c96c19a100d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 2 Feb 2015 20:52:37 +0600 Subject: [PATCH] [historicfilms] Add extractor (Closes #4825) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/historicfilms.py | 46 +++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 youtube_dl/extractor/historicfilms.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9c14b096f..dabf86ec8 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -182,6 +182,7 @@ from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE +from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE from .hornbunny import HornBunnyIE from .hostingbulk import HostingBulkIE diff --git a/youtube_dl/extractor/historicfilms.py b/youtube_dl/extractor/historicfilms.py new file mode 100644 index 000000000..40afbe537 --- /dev/null +++ b/youtube_dl/extractor/historicfilms.py @@ -0,0 +1,46 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import parse_duration + + +class HistoricFilmsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P\d+)' + _TEST = { + 'url': 'http://www.historicfilms.com/tapes/4728', + 'md5': 'd4a437aec45d8d796a38a215db064e9a', + 'info_dict': { + 'id': '4728', + 'ext': 'mov', + 'title': 'Historic Films: GP-7', + 'description': 'md5:1a86a0f3ac54024e419aba97210d959a', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2096, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + tape_id = self._search_regex( + r'class="tapeId">([^<]+)<', webpage, 'tape id') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._html_search_meta( + 'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage) + duration = parse_duration(self._html_search_meta( + 'duration', webpage, 'duration')) + + video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + }