From 05d4612947d6dbfaedb8f2a00daa5f29d85f73df Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Thu, 1 Sep 2016 16:58:16 +0800 Subject: [movingimage] Adapt to the new domain name and fix extraction Closes #10466 --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/movingimage.py | 52 +++++++++++++++++++++++++++++++++ youtube_dl/extractor/ssa.py | 58 ------------------------------------- 3 files changed, 53 insertions(+), 59 deletions(-) create mode 100644 youtube_dl/extractor/movingimage.py delete mode 100644 youtube_dl/extractor/ssa.py (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 21efa96b2..8d0688f53 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -486,6 +486,7 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE +from .movingimage import MovingImageIE from .msn import MSNIE from .mtv import ( MTVIE, @@ -806,7 +807,6 @@ from .srgssr import ( SRGSSRPlayIE, ) from .srmediathek import SRMediathekIE -from .ssa import SSAIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamable import StreamableIE diff --git a/youtube_dl/extractor/movingimage.py b/youtube_dl/extractor/movingimage.py new file mode 100644 index 000000000..bb789c32e --- /dev/null +++ b/youtube_dl/extractor/movingimage.py @@ -0,0 +1,52 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unescapeHTML, + parse_duration, +) + + +class MovingImageIE(InfoExtractor): + _VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P\d+)' + _TEST = { + 'url': 'http://movingimage.nls.uk/film/3561', + 'md5': '4caa05c2b38453e6f862197571a7be2f', + 'info_dict': { + 'id': '3561', + 'ext': 'mp4', + 'title': 'SHETLAND WOOL', + 'description': 'md5:c5afca6871ad59b4271e7704fe50ab04', + 'duration': 900, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + formats = self._extract_m3u8_formats( + self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'), + video_id, ext='mp4', entry_protocol='m3u8_native') + + def search_field(field_name, fatal=False): + return self._search_regex( + r'%s:\s*([^<]+)' % field_name, + webpage, 'title', fatal=fatal) + + title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]') + description = unescapeHTML(search_field('Description')) + duration = parse_duration(search_field('Running time')) + thumbnail = self._search_regex( + r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/ssa.py b/youtube_dl/extractor/ssa.py deleted file mode 100644 index 54d1843f2..000000000 --- a/youtube_dl/extractor/ssa.py +++ /dev/null @@ -1,58 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - unescapeHTML, - parse_duration, -) - - -class SSAIE(InfoExtractor): - _VALID_URL = r'https?://ssa\.nls\.uk/film/(?P\d+)' - _TEST = { - 'url': 'http://ssa.nls.uk/film/3561', - 'info_dict': { - 'id': '3561', - 'ext': 'flv', - 'title': 'SHETLAND WOOL', - 'description': 'md5:c5afca6871ad59b4271e7704fe50ab04', - 'duration': 900, - 'thumbnail': 're:^https?://.*\.jpg$', - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - streamer = self._search_regex( - r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer') - play_path = self._search_regex( - r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0] - - def search_field(field_name, fatal=False): - return self._search_regex( - r'%s:\s*([^<]+)' % field_name, - webpage, 'title', fatal=fatal) - - title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]') - description = unescapeHTML(search_field('Description')) - duration = parse_duration(search_field('Running time')) - thumbnail = self._search_regex( - r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False) - - return { - 'id': video_id, - 'url': streamer, - 'play_path': play_path, - 'ext': 'flv', - 'title': title, - 'description': description, - 'duration': duration, - 'thumbnail': thumbnail, - } -- cgit v1.2.3