From: Yen Chi Hsuan Date: Sat, 8 Jul 2017 07:48:05 +0000 (+0800) Subject: [yam] Remove extractor X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=eadd313321f4fbacac2ec10f2f382197e401d7f7;p=youtube-dl [yam] Remove extractor mymedia.yam.com is dead. An wikipedia user also pointed out that Yam's blog service is no longer available. [1] [1] https://zh.wikipedia.org/zh-tw/%E5%A4%A9%E7%A9%BA%E9%83%A8%E8%90%BD --- diff --git a/ChangeLog b/ChangeLog index 4c2011326..5d07c12cb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors +- [yam] Remove extractor + + version 2017.07.02 Core diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index bbdb4a2fe..b83c3aba5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1280,7 +1280,6 @@ from .yahoo import ( YahooIE, YahooSearchIE, ) -from .yam import YamIE from .yandexmusic import ( YandexMusicTrackIE, YandexMusicAlbumIE, diff --git a/youtube_dl/extractor/yam.py b/youtube_dl/extractor/yam.py deleted file mode 100644 index ef5535547..000000000 --- a/youtube_dl/extractor/yam.py +++ /dev/null @@ -1,123 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_urlparse -from ..utils import ( - float_or_none, - month_by_abbreviation, - ExtractorError, - get_element_by_attribute, -) - - -class YamIE(InfoExtractor): - IE_DESC = '蕃薯藤yam天空部落' - _VALID_URL = r'https?://mymedia\.yam\.com/m/(?P\d+)' - - _TESTS = [{ - # An audio hosted on Yam - 'url': 'http://mymedia.yam.com/m/2283921', - 'md5': 'c011b8e262a52d5473d9c2e3c9963b9c', - 'info_dict': { - 'id': '2283921', - 'ext': 'mp3', - 'title': '發現 - 趙薇 京華煙雲主題曲', - 'description': '發現 - 趙薇 京華煙雲主題曲', - 'uploader_id': 'princekt', - 'upload_date': '20080807', - 'duration': 313.0, - } - }, { - # An external video hosted on YouTube - 'url': 'http://mymedia.yam.com/m/3599430', - 'md5': '03127cf10d8f35d120a9e8e52e3b17c6', - 'info_dict': { - 'id': 'CNpEoQlrIgA', - 'ext': 'mp4', - 'upload_date': '20150306', - 'uploader': '新莊社大瑜伽社', - 'description': 'md5:11e2e405311633ace874f2e6226c8b17', - 'uploader_id': '2323agoy', - 'title': '20090412陽明山二子坪-1', - }, - 'skip': 'Video does not exist', - }, { - 'url': 'http://mymedia.yam.com/m/3598173', - 'info_dict': { - 'id': '3598173', - 'ext': 'mp4', - }, - 'skip': 'cause Yam system error', - }, { - 'url': 'http://mymedia.yam.com/m/3599437', - 'info_dict': { - 'id': '3599437', - 'ext': 'mp4', - }, - 'skip': 'invalid YouTube URL', - }, { - 'url': 'http://mymedia.yam.com/m/2373534', - 'md5': '7ff74b91b7a817269d83796f8c5890b1', - 'info_dict': { - 'id': '2373534', - 'ext': 'mp3', - 'title': '林俊傑&蔡卓妍-小酒窩', - 'description': 'md5:904003395a0fcce6cfb25028ff468420', - 'upload_date': '20080928', - 'uploader_id': 'onliner2', - } - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - page = self._download_webpage(url, video_id) - - # Check for errors - system_msg = self._html_search_regex( - r'系統訊息(?:
|\n|\r)*([^<>]+)
', page, 'system message', - default=None) - if system_msg: - raise ExtractorError(system_msg, expected=True) - - # Is it hosted externally on YouTube? - youtube_url = self._html_search_regex( - r']+class="heading"[^>]*>\s*(.+)\s*', page, 'title') - - api_page = self._download_webpage( - 'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id, - note='Downloading API page') - api_result_obj = compat_urlparse.parse_qs(api_page) - - info_table = get_element_by_attribute('class', 'info', page) - uploader_id = self._html_search_regex( - r':[\n ]+(?P[A-Z][a-z]{2})\s+' + - r'(?P\d{1,2}), (?P\d{4})', page) - if mobj: - upload_date = '%s%02d%02d' % ( - mobj.group('year'), - month_by_abbreviation(mobj.group('mon')), - int(mobj.group('day'))) - else: - upload_date = None - duration = float_or_none(api_result_obj['totaltime'][0], scale=1000) - - return { - 'id': video_id, - 'url': api_result_obj['mp3file'][0], - 'title': title, - 'description': self._html_search_meta('description', page), - 'duration': duration, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - }