From 2f0a33d8a3c926f3a81d0e76bd669a8bc57a2cf8 Mon Sep 17 00:00:00 2001 From: ping Date: Sat, 30 Jan 2016 20:10:36 +0800 Subject: [PATCH] [daum.net] Support for playlists, user channels --- youtube_dl/extractor/__init__.py | 2 + youtube_dl/extractor/daum.py | 119 ++++++++++++++++++++++++++++++- 2 files changed, 120 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5e0d7d3dcc..e05d986efd 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -142,6 +142,8 @@ from .dailymotion import ( from .daum import ( DaumIE, DaumClipIE, + DaumPlaylistIE, + DaumUserIE, ) from .dbtv import DBTVIE from .dcn import ( diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 9bc345f607..cf158c42d6 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re +import itertools from .common import InfoExtractor from ..compat import ( @@ -13,6 +14,7 @@ from ..utils import ( int_or_none, str_to_int, xpath_text, + unescapeHTML, ) @@ -143,7 +145,7 @@ class DaumClipIE(InfoExtractor): '_type': 'url_transparent', 'id': video_id, 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'], - 'title': clip_info['title'], + 'title': unescapeHTML(clip_info['title']), 'thumbnail': clip_info.get('thumb_url'), 'description': clip_info.get('contents'), 'duration': int_or_none(clip_info.get('duration')), @@ -151,3 +153,118 @@ class DaumClipIE(InfoExtractor): 'view_count': int_or_none(clip_info.get('play_count')), 'ie_key': 'Daum', } + + +class DaumListIE(InfoExtractor): + def _get_entries(self, list_id, list_id_type): + name = None + entries = [] + for pagenum in itertools.count(1): + list_info = self._download_json( + 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?size=48&init=true&order=date&page=%d&%s=%s' % ( + pagenum, list_id_type, list_id), list_id,'Downloading list info - %s' % pagenum) + + entries.extend([ + self.url_result( + 'http://tvpot.daum.net/v/%s' % clip['vid']) + for clip in list_info['clip_list'] + ]) + + if not name: + name = list_info.get('playlist_bean', {}).get('name') or \ + list_info.get('potInfo', {}).get('name') + + if not list_info.get('has_more'): + break + + return name, entries + + +class DaumPlaylistIE(DaumListIE): + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View\.do|Top\.tv)\?.*?playlistid=(?P[0-9]+)' + IE_NAME = 'daum.net:playlist' + + _TESTS = [{ + 'note': 'Playlist url with clipid', + 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844', + 'info_dict': { + 'id': '6213966', + 'title': 'Woorissica Official', + }, + 'playlist_mincount': 181 + }, { + 'note': 'Playlist url with clipid - noplaylist', + 'url': 'http://tvpot.daum.net/mypot/View.do?playlistid=6213966&clipid=73806844', + 'info_dict': { + 'id': '73806844', + 'ext': 'mp4', + 'title': '151017 Airport', + 'upload_date': '20160117', + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, + } + }] + + def _real_extract(self, url): + if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'): + return self.url_result(url, 'DaumClip') + + list_id = self._match_id(url) + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id) + + name, entries = self._get_entries(list_id, 'playlistid') + + return self.playlist_result(entries, list_id, name) + + +class DaumUserIE(DaumListIE): + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/mypot/(?:View|Top)\.do\?.*?ownerid=(?P[0-9a-zA-Z]+)' + IE_NAME = 'daum.net:user' + + _TESTS = [{ + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0', + 'info_dict': { + 'id': 'o2scDLIVbHc0', + 'title': '마이 리틀 텔레비전', + }, + 'playlist_mincount': 213 + }, { + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&clipid=73801156', + 'info_dict': { + 'id': '73801156', + 'ext': 'mp4', + 'title': '[미공개] 김구라, 오만석이 부릅니다 \'오케피\' - 마이 리틀 텔레비전 20160116', + 'upload_date': '20160117', + 'description': 'md5:5e91d2d6747f53575badd24bd62b9f36' + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, + } + }, { + 'note': 'Playlist url has ownerid and playlistid, playlistid takes precedence', + 'url': 'http://tvpot.daum.net/mypot/View.do?ownerid=o2scDLIVbHc0&playlistid=6196631', + 'info_dict': { + 'id': '6196631', + 'title': '마이 리틀 텔레비전 - 20160109', + }, + 'playlist_count': 11 + }, { + 'url': 'http://tvpot.daum.net/mypot/Top.do?ownerid=o2scDLIVbHc0', + 'only_matching': True, + }] + + def _real_extract(self, url): + if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'): + return self.url_result(url, 'DaumClip') + + if DaumPlaylistIE.suitable(url): + return self.url_result(url, 'DaumPlaylist') + + list_id = self._match_id(url) + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id) + name, entries = self._get_entries(list_id, 'ownerid') + + return self.playlist_result(entries, list_id, name)