From 2f0a33d8a3c926f3a81d0e76bd669a8bc57a2cf8 Mon Sep 17 00:00:00 2001 From: ping Date: Sat, 30 Jan 2016 20:10:36 +0800 Subject: [PATCH 1/4] [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 5e0d7d3dc..e05d986ef 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 9bc345f60..cf158c42d 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) From 7537b35fb80061287f6901bcdb6b3f6aae558036 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 1 Feb 2016 17:40:35 +0800 Subject: [PATCH 2/4] [daum] PEP8 --- youtube_dl/extractor/daum.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index cf158c42d..67c4c7c6b 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -162,8 +162,8 @@ class DaumListIE(InfoExtractor): 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) - + 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']) From 11a4efc505fdb6456b00e848609523bb7b8e344c Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 1 Feb 2016 18:15:53 +0800 Subject: [PATCH 3/4] [daum] Do not match a single URL with multiple info extractors --- youtube_dl/extractor/daum.py | 47 +++++++++++++++++++++++++++--------- 1 file changed, 36 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 67c4c7c6b..5a7565e96 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -7,8 +7,10 @@ import itertools from .common import InfoExtractor from ..compat import ( + compat_parse_qs, compat_urllib_parse, compat_urllib_parse_unquote, + compat_urlparse, ) from ..utils import ( int_or_none, @@ -117,6 +119,7 @@ class DaumIE(InfoExtractor): class DaumClipIE(InfoExtractor): _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P\d+)' IE_NAME = 'daum.net:clip' + _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s' _TESTS = [{ 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', @@ -135,6 +138,10 @@ class DaumClipIE(InfoExtractor): 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if DaumPlaylistIE.suitable(url) or DaumUserIE.suitable(url) else super(DaumClipIE, cls).suitable(url) + def _real_extract(self, url): video_id = self._match_id(url) clip_info = self._download_json( @@ -179,10 +186,21 @@ class DaumListIE(InfoExtractor): return name, entries + def _check_clip(self, url, list_id): + query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query) + if 'clipid' in query_dict: + clip_id = query_dict['clipid'][0] + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just video %s because of --no-playlist' % clip_id) + return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip') + else: + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id) + 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' + _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s' _TESTS = [{ 'note': 'Playlist url with clipid', @@ -207,12 +225,16 @@ class DaumPlaylistIE(DaumListIE): } }] - def _real_extract(self, url): - if DaumClipIE.suitable(url) and self._downloader.params.get('noplaylist'): - return self.url_result(url, 'DaumClip') + @classmethod + def suitable(cls, url): + return False if DaumUserIE.suitable(url) else super(DaumPlaylistIE, cls).suitable(url) + def _real_extract(self, url): list_id = self._match_id(url) - self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id) + + clip_result = self._check_clip(url, list_id) + if clip_result: + return clip_result name, entries = self._get_entries(list_id, 'playlistid') @@ -257,14 +279,17 @@ class DaumUserIE(DaumListIE): }] 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) + + clip_result = self._check_clip(url, list_id) + if clip_result: + return clip_result + + query_dict = compat_parse_qs(compat_urlparse.urlparse(url).query) + if 'playlistid' in query_dict: + playlist_id = query_dict['playlistid'][0] + return self.url_result(DaumPlaylistIE._URL_TEMPLATE % playlist_id, 'DaumPlaylist') + name, entries = self._get_entries(list_id, 'ownerid') return self.playlist_result(entries, list_id, name) From 58250eff2b1cd8968d17d88c8e8fbefdfd9b0a68 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 1 Feb 2016 18:19:02 +0800 Subject: [PATCH 4/4] [daum] Update test_daum_1 --- youtube_dl/extractor/daum.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 5a7565e96..9fce845e1 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -42,7 +42,7 @@ class DaumIE(InfoExtractor): 'info_dict': { 'id': '65139429', 'ext': 'mp4', - 'title': 'md5:a100d65d09cec246d8aa9bde7de45aed', + 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118', 'description': 'md5:79794514261164ff27e36a21ad229fc5', 'upload_date': '20150604', 'thumbnail': 're:^https?://.*\.(?:jpg|png)',