From 8e70c1bfac98b3d0d304b66ff1d616dd26522acb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 15 Mar 2018 22:37:41 +0700 Subject: [PATCH] [heise] Improve extraction (closes #15496, closes #15784, closes #15026) --- youtube_dl/extractor/heise.py | 76 +++++++++++++++++++++++++---------- 1 file changed, 54 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py index 8f49f52ef..5c03780a3 100644 --- a/youtube_dl/extractor/heise.py +++ b/youtube_dl/extractor/heise.py @@ -7,6 +7,7 @@ from ..utils import ( determine_ext, int_or_none, + NO_DEFAULT, parse_iso8601, smuggle_url, xpath_text, @@ -16,18 +17,19 @@ class HeiseIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P[0-9]+)\.html' _TESTS = [{ + # kaltura embed 'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html', - 'md5': 'ffed432483e922e88545ad9f2f15d30e', 'info_dict': { - 'id': '2404147', + 'id': '1_kkrq94sm', 'ext': 'mp4', 'title': "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone", - 'format_id': 'mp4_720p', - 'timestamp': 1411812600, - 'upload_date': '20140927', + 'timestamp': 1512734959, + 'upload_date': '20171208', 'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20', - 'thumbnail': r're:^https?://.*/gallery/$', - } + }, + 'params': { + 'skip_download': True, + }, }, { # YouTube embed 'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html', @@ -46,13 +48,26 @@ class HeiseIE(InfoExtractor): }, }, { 'url': 'https://www.heise.de/video/artikel/nachgehakt-Wie-sichert-das-c-t-Tool-Restric-tor-Windows-10-ab-3700244.html', - 'md5': '4b58058b46625bdbd841fc2804df95fc', 'info_dict': { 'id': '1_ntrmio2s', + 'ext': 'mp4', + 'title': "nachgehakt: Wie sichert das c't-Tool Restric'tor Windows 10 ab?", + 'description': 'md5:47e8ffb6c46d85c92c310a512d6db271', 'timestamp': 1512470717, 'upload_date': '20171205', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.heise.de/ct/artikel/c-t-uplink-20-8-Staubsaugerroboter-Xiaomi-Vacuum-2-AR-Brille-Meta-2-und-Android-rooten-3959893.html', + 'info_dict': { + 'id': '1_59mk80sf', 'ext': 'mp4', - 'title': 'ct10 nachgehakt hos restrictor', + 'title': "c't uplink 20.8: Staubsaugerroboter Xiaomi Vacuum 2, AR-Brille Meta 2 und Android rooten", + 'description': 'md5:f50fe044d3371ec73a8f79fcebd74afc', + 'timestamp': 1517567237, + 'upload_date': '20180202', }, 'params': { 'skip_download': True, @@ -72,19 +87,40 @@ def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_meta('fulltitle', webpage, default=None) - if not title or title == "c't": - title = self._search_regex( - r']+class="videoplayerjw"[^>]+data-title="([^"]+)"', - webpage, 'title') + def extract_title(default=NO_DEFAULT): + title = self._html_search_meta( + ('fulltitle', 'title'), webpage, default=None) + if not title or title == "c't": + title = self._search_regex( + r']+class="videoplayerjw"[^>]+data-title="([^"]+)"', + webpage, 'title', default=None) + if not title: + title = self._html_search_regex( + r']+\bclass=["\']article_page_title[^>]+>(.+?)<', + webpage, 'title', default=default) + return title - yt_urls = YoutubeIE._extract_urls(webpage) - if yt_urls: - return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key()) + title = extract_title(default=None) + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'description', webpage) kaltura_url = KalturaIE._extract_url(webpage) if kaltura_url: - return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key()) + return { + '_type': 'url_transparent', + 'url': smuggle_url(kaltura_url, {'source_url': url}), + 'ie_key': KalturaIE.ie_key(), + 'title': title, + 'description': description, + } + + yt_urls = YoutubeIE._extract_urls(webpage) + if yt_urls: + return self.playlist_from_matches( + yt_urls, video_id, title, ie=YoutubeIE.ie_key()) + + title = extract_title() container_id = self._search_regex( r'
]+data-container="([0-9]+)"', @@ -115,10 +151,6 @@ def _real_extract(self, url): }) self._sort_formats(formats) - description = self._og_search_description( - webpage, default=None) or self._html_search_meta( - 'description', webpage) - return { 'id': video_id, 'title': title,