From f58487b392f7943c31e41b200bef8e97822529db Mon Sep 17 00:00:00 2001 From: Thijs Vermeir Date: Fri, 2 Jan 2015 13:13:18 +0100 Subject: [PATCH 1/2] [vier] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vier.py | 75 ++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) create mode 100644 youtube_dl/extractor/vier.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9848ff611..9ccd1b32e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -474,6 +474,7 @@ from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE +from .vier import VierIE, VierVideosIE from .vimeo import ( VimeoIE, VimeoAlbumIE, diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py new file mode 100644 index 000000000..e3f1b4714 --- /dev/null +++ b/youtube_dl/extractor/vier.py @@ -0,0 +1,75 @@ +from .common import InfoExtractor +from ..utils import escape_url + +import re + +class VierIE (InfoExtractor): + _VALID_URL = r'(?:http://)?www.vier.be/(?P.*)/videos/(.+?)/(?P\d*)' + _TEST = { + 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'md5': 'bf48f4eb998cbde44ecd02fc42c51149', + 'info_dict': { + 'id': '16129', + 'ext': 'mp4', + 'title': 'Het wordt warm in De Moestuin', + 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + }, + } + + def _real_extract (self, url): + mobj = re.match (self._VALID_URL, url) + + program = mobj.group ('program') + video_id = mobj.group ('id') + + webpage = self._download_webpage (url, video_id) + + title = self._html_search_regex(r'', webpage, u'title') + description = self._html_search_regex (r'', webpage, u'description') + vod_id = self._html_search_regex(r'"filename" : "(.+?)"', webpage, u'playlist URL') + url = escape_url ("http://vod.streamcloud.be/vier_vod/mp4:_definst_/" + vod_id + ".mp4/playlist.m3u8") + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'formats': self._extract_m3u8_formats(url, video_id, 'mp4'), + } + +class VierVideosIE (InfoExtractor): + _VALID_URL = r'http://www.vier.be/(?P.*)/videos(\?page=(?P\d*))?$' + _TESTS = [{ + 'url': 'http://www.vier.be/demoestuin/videos', + 'info_dict': { + 'id': 'demoestuin page(0)', + }, + 'playlist_mincount': 20, + }, + { + 'url': 'http://www.vier.be/demoestuin/videos?page=6', + 'info_dict': { + 'id': 'demoestuin page(6)', + }, + 'playlist_mincount': 20, + }] + + def _real_extract (self, url): + mobj = re.match (self._VALID_URL, url) + + program = mobj.group ('program') + page = mobj.group ('page') + if page == None: + page = 0 + + videos_id = program + " page(" + str (page) + ")" + videos_page = self._download_webpage (url, videos_id, note='Retrieving videos page') + + return { + '_type': 'playlist', + 'id': videos_id, + 'entries': [{ + '_type': 'url', + 'url': "http://www.vier.be/" + eurl[0], + 'ie_key': 'Vier', + } for eurl in re.findall (r'

(.+?)

', videos_page)] + } From 9eb4f404cbd10268befa47a1bcf699f07a47f5de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 2 Jan 2015 20:15:40 +0600 Subject: [PATCH 2/2] [vier] Simplify, add support for more URL formats, extract all playlist pages when page is not specified --- youtube_dl/extractor/vier.py | 185 +++++++++++++++++++++-------------- 1 file changed, 114 insertions(+), 71 deletions(-) diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index e3f1b4714..fe54ae475 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -1,75 +1,118 @@ -from .common import InfoExtractor -from ..utils import escape_url +# coding: utf-8 +from __future__ import unicode_literals import re -class VierIE (InfoExtractor): - _VALID_URL = r'(?:http://)?www.vier.be/(?P.*)/videos/(.+?)/(?P\d*)' - _TEST = { - 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', - 'md5': 'bf48f4eb998cbde44ecd02fc42c51149', - 'info_dict': { - 'id': '16129', - 'ext': 'mp4', - 'title': 'Het wordt warm in De Moestuin', - 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', - }, - } - - def _real_extract (self, url): - mobj = re.match (self._VALID_URL, url) - - program = mobj.group ('program') - video_id = mobj.group ('id') - - webpage = self._download_webpage (url, video_id) - - title = self._html_search_regex(r'', webpage, u'title') - description = self._html_search_regex (r'', webpage, u'description') - vod_id = self._html_search_regex(r'"filename" : "(.+?)"', webpage, u'playlist URL') - url = escape_url ("http://vod.streamcloud.be/vier_vod/mp4:_definst_/" + vod_id + ".mp4/playlist.m3u8") - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'formats': self._extract_m3u8_formats(url, video_id, 'mp4'), - } - -class VierVideosIE (InfoExtractor): - _VALID_URL = r'http://www.vier.be/(?P.*)/videos(\?page=(?P\d*))?$' - _TESTS = [{ - 'url': 'http://www.vier.be/demoestuin/videos', - 'info_dict': { - 'id': 'demoestuin page(0)', - }, - 'playlist_mincount': 20, - }, - { - 'url': 'http://www.vier.be/demoestuin/videos?page=6', - 'info_dict': { - 'id': 'demoestuin page(6)', - }, - 'playlist_mincount': 20, - }] - - def _real_extract (self, url): - mobj = re.match (self._VALID_URL, url) - - program = mobj.group ('program') - page = mobj.group ('page') - if page == None: - page = 0 - - videos_id = program + " page(" + str (page) + ")" - videos_page = self._download_webpage (url, videos_id, note='Retrieving videos page') - - return { - '_type': 'playlist', - 'id': videos_id, - 'entries': [{ - '_type': 'url', - 'url': "http://www.vier.be/" + eurl[0], - 'ie_key': 'Vier', - } for eurl in re.findall (r'

(.+?)

', videos_page)] +from .common import InfoExtractor + + +class VierIE(InfoExtractor): + IE_NAME = 'vier' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P[^/]+)(?:/(?P\d+))?|video/v3/embed/(?P\d+))' + _TESTS = [{ + 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'info_dict': { + 'id': '16129', + 'display_id': 'het-wordt-warm-de-moestuin', + 'ext': 'mp4', + 'title': 'Het wordt warm in De Moestuin', + 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen', + 'only_matching': True, + }, { + 'url': 'http://www.vier.be/video/v3/embed/16129', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + embed_id = mobj.group('embed_id') + display_id = mobj.group('display_id') or embed_id + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') + application = self._search_regex( + r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') + filename = self._search_regex( + r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + + playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) + formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') + + title = self._og_search_title(webpage, default=display_id) + description = self._og_search_description(webpage, default=None) + thumbnail = self._og_search_thumbnail(webpage, default=None) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, } + + +class VierVideosIE(InfoExtractor): + IE_NAME = 'vier:videos' + _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P[^/]+)/videos(?:\?page=(?P\d+))?$' + _TESTS = [{ + 'url': 'http://www.vier.be/demoestuin/videos', + 'info_dict': { + 'id': 'demoestuin', + }, + 'playlist_mincount': 153, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=6', + 'info_dict': { + 'id': 'demoestuin-page6', + }, + 'playlist_mincount': 20, + }, { + 'url': 'http://www.vier.be/demoestuin/videos?page=7', + 'info_dict': { + 'id': 'demoestuin-page7', + }, + 'playlist_mincount': 13, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + program = mobj.group('program') + + webpage = self._download_webpage(url, program) + + page_id = mobj.group('page') + if page_id: + page_id = int(page_id) + start_page = page_id + last_page = start_page + 1 + playlist_id = '%s-page%d' % (program, page_id) + else: + start_page = 0 + last_page = int(self._search_regex( + r'videos\?page=(\d+)">laatste', + webpage, 'last page', default=0)) + 1 + playlist_id = program + + entries = [] + for current_page_id in range(start_page, last_page): + current_page = self._download_webpage( + 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id), + program, + 'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage + page_entries = [ + self.url_result('http://www.vier.be' + video_url, 'Vier') + for video_url in re.findall( + r'

', current_page)] + entries.extend(page_entries) + + return self.playlist_result(entries, playlist_id)