X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/7ceb2ec430c3363e0140a0519402428f36dc472e..dd50658396011c8e98b7201f035408b7959d56e1:/youtube_dl/extractor/daum.py

diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py
index a804e83..76f0218 100644
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -1,74 +1,308 @@
-# encoding: utf-8
+# coding: utf-8
+
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
+import itertools
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,
+    compat_urlparse,
+)
 from ..utils import (
-    compat_urllib_parse,
-    determine_ext,
+    int_or_none,
+    str_to_int,
+    xpath_text,
+    unescapeHTML,
 )
 
 
 class DaumIE(InfoExtractor):
-    _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
-    IE_NAME = u'daum.net'
-
-    _TEST = {
-        u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
-        u'file': u'52554690.mp4',
-        u'info_dict': {
-            u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'upload_date': u'20130831',
-            u'duration': 3868,
+    _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
+    IE_NAME = 'daum.net'
+
+    _TESTS = [{
+        'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
+        'info_dict': {
+            'id': 'vab4dyeDBysyBssyukBUjBz',
+            'ext': 'mp4',
+            'title': '마크 헌트 vs 안토니오 실바',
+            'description': 'Mark Hunt vs Antonio Silva',
+            'upload_date': '20131217',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'duration': 2117,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        'url': 'http://m.tvpot.daum.net/v/65139429',
+        'info_dict': {
+            'id': '65139429',
+            'ext': 'mp4',
+            'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
+            'description': 'md5:79794514261164ff27e36a21ad229fc5',
+            'upload_date': '20150604',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'duration': 154,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
+        'only_matching': True,
+    }, {
+        'url': 'http://videofarm.daum.net/controller/player/VodPlayer.swf?vid=vwIpVpCQsT8%24&ref=',
+        'info_dict': {
+            'id': 'vwIpVpCQsT8$',
+            'ext': 'flv',
+            'title': '01-Korean War ( Trouble on the horizon )',
+            'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
+            'upload_date': '20080223',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'duration': 249,
+            'view_count': int,
+            'comment_count': int,
+        },
+    }, {
+        # Requires dte_type=WEB (#9972)
+        'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU',
+        'md5': 'a8917742069a4dd442516b86e7d66529',
+        'info_dict': {
+            'id': 's3794Uf1NZeZ1qMpGpeqeRU',
+            'ext': 'mp4',
+            'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
+            'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
+            'upload_date': '20160611',
         },
-    }
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
-        webpage = self._download_webpage(canonical_url, video_id)
-        full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
-            webpage, u'full id')
-        query = compat_urllib_parse.urlencode({'vid': full_id})
-        info_xml = self._download_webpage(
-            'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
-            u'Downloading video info')
-        urls_xml = self._download_webpage(
-            'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
-            video_id, u'Downloading video formats info')
-        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
-        urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
-
-        self.to_screen(u'%s: Getting video urls' % video_id)
+        video_id = compat_urllib_parse_unquote(self._match_id(url))
+        movie_data = self._download_json(
+            'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
+            video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
+
+        # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
+        if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
+            return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
+
+        info = self._download_xml(
+            'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
+            'Downloading video info', query={'vid': video_id})
+
         formats = []
-        for format_el in urls.findall('result/output_list/output_list'):
-            profile = format_el.attrib['profile']
-            format_query = compat_urllib_parse.urlencode({
-                'vid': full_id,
+        for format_el in movie_data['output_list']['output_list']:
+            profile = format_el['profile']
+            format_query = compat_urllib_parse_urlencode({
+                'vid': video_id,
                 'profile': profile,
             })
-            url_xml = self._download_webpage(
+            url_doc = self._download_xml(
                 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
-                video_id, note=False)
-            url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
+                video_id, note='Downloading video data for %s format' % profile)
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
-                'ext': determine_ext(format_url),
                 'format_id': profile,
+                'width': int_or_none(format_el.get('width')),
+                'height': int_or_none(format_el.get('height')),
+                'filesize': int_or_none(format_el.get('filesize')),
             })
+        self._sort_formats(formats)
 
-        info = {
+        return {
             'id': video_id,
             'title': info.find('TITLE').text,
             'formats': formats,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'description': info.find('CONTENTS').text,
-            'duration': int(info.find('DURATION').text),
+            'thumbnail': xpath_text(info, 'THUMB_URL'),
+            'description': xpath_text(info, 'CONTENTS'),
+            'duration': int_or_none(xpath_text(info, 'DURATION')),
             'upload_date': info.find('REGDTTM').text[:8],
+            'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
+            'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
+        }
+
+
+class DaumClipIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\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',
+        'info_dict': {
+            'id': '52554690',
+            'ext': 'mp4',
+            'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'upload_date': '20130831',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'duration': 3868,
+            'view_count': int,
+        },
+    }, {
+        'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
+        '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(
+            'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
+            video_id, 'Downloading clip info')['clip_bean']
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
+            'title': unescapeHTML(clip_info['title']),
+            'thumbnail': clip_info.get('thumb_url'),
+            'description': clip_info.get('contents'),
+            'duration': int_or_none(clip_info.get('duration')),
+            'upload_date': clip_info.get('up_date')[:8],
+            '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
+
+    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<id>[0-9]+)'
+    IE_NAME = 'daum.net:playlist'
+    _URL_TEMPLATE = 'http://tvpot.daum.net/mypot/View.do?playlistid=%s'
+
+    _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,
+        }
+    }]
+
+    @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)
+
+        clip_result = self._check_clip(url, list_id)
+        if clip_result:
+            return clip_result
+
+        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|tv)\?.*?ownerid=(?P<id>[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,
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info
+    }, {
+        '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,
+    }, {
+        'url': 'http://m.tvpot.daum.net/mypot/Top.tv?ownerid=45x1okb1If50&playlistid=3569733',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+
+        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)