Merge remote-tracking branch 'jtwaleson/master'

diff --git a/AUTHORS b/AUTHORS
index 5ec2f1dc744cc8ecae9e7250f9ccbf772e24f608..c8d60282c04c7138efe3f70a8116d12fcced2640 100644 (file)
--- a/AUTHORS
+++ b/AUTHORS
@@ -84,3 +84,4 @@ xantares
 Jan Matějka
 Mauroy Sébastien
 William Sewell
+Dao Hoang Son

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 43185345ec33a52f1fd1c2cf12bbb54f71781cc1..fb5e6ac77d5680238579a765c0f341a5cff0b68c 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -511,6 +511,10 @@ from .youtube import (
     YoutubeWatchLaterIE,
 )
 from .zdf import ZDFIE
+from .zingmp3 import (
+    ZingMp3SongIE,
+    ZingMp3AlbumIE,
+)
 
 _ALL_CLASSES = [
     klass

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index fa3ead95b00281e53f61626c9b26c359efa0e950..4ebc7b7129e0a5d2f04a6a3a01f32018df75b502 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -1567,14 +1567,14 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
 
 
 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'YouTube.com recommended videos, "ytrec" keyword (requires authentication)'
+    IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
     _FEED_NAME = 'recommended'
     _PLAYLIST_TITLE = 'Youtube Recommended videos'
 
 
 class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'Youtube watch later list, "ytwatchlater" keyword (requires authentication)'
+    IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater'
     _FEED_NAME = 'watch_later'
     _PLAYLIST_TITLE = 'Youtube Watch Later'
@@ -1582,7 +1582,7 @@ class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
 
 
 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'Youtube watch history, "ythistory" keyword (requires authentication)'
+    IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
     _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
     _FEED_NAME = 'history'
     _PERSONAL_FEED = True
@@ -1591,7 +1591,7 @@ class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
 
 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
     IE_NAME = 'youtube:favorites'
-    IE_DESC = 'YouTube.com favourite videos, "ytfav" keyword (requires authentication)'
+    IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
     _LOGIN_REQUIRED = True
 

diff --git a/youtube_dl/extractor/zingmp3.py b/youtube_dl/extractor/zingmp3.py
new file mode 100644 (file)
index 0000000..1afbe68
--- /dev/null
+++ b/youtube_dl/extractor/zingmp3.py
@@ -0,0 +1,107 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class ZingMp3BaseInfoExtractor(InfoExtractor):
+
+    @staticmethod
+    def _extract_item(item):
+        title = item.find('./title').text.strip()
+        source = item.find('./source').text
+        extension = item.attrib['type']
+        thumbnail = item.find('./backimage').text
+
+        return {
+            'title': title,
+            'url': source,
+            'ext': extension,
+            'thumbnail': thumbnail,
+        }
+
+    def _extract_player_xml(self, player_xml_url, id, playlist_title=None):
+        player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML')
+        items = player_xml.findall('./item')
+
+        if len(items) == 1:
+            # one single song
+            data = self._extract_item(items[0])
+            data['id'] = id
+
+            return data
+        else:
+            # playlist of songs
+            entries = []
+
+            for i, item in enumerate(items, 1):
+                entry = self._extract_item(item)
+                entry['id'] = '%s-%d' % (id, i)
+                entries.append(entry)
+
+            return {
+                '_type': 'playlist',
+                'id': id,
+                'title': playlist_title,
+                'entries': entries,
+            }
+
+
+class ZingMp3SongIE(ZingMp3BaseInfoExtractor):
+    _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html'
+    _TESTS = [{
+        'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
+        'md5': 'ead7ae13693b3205cbc89536a077daed',
+        'info_dict': {
+            'id': 'ZWZB9WAB',
+            'title': 'Xa Mãi Xa',
+            'ext': 'mp3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }]
+    IE_NAME = 'zingmp3:song'
+    IE_DESC = 'mp3.zing.vn songs'
+
+    def _real_extract(self, url):
+        matched = re.match(self._VALID_URL, url)
+        slug = matched.group('slug')
+        song_id = matched.group('song_id')
+
+        webpage = self._download_webpage(
+            'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id)
+
+        player_xml_url = self._search_regex(
+            r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
+
+        return self._extract_player_xml(player_xml_url, song_id)
+
+
+class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
+    _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
+    _TESTS = [{
+        'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'ZWZBWDAF',
+            'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless',
+        },
+        'playlist_count': 10,
+    }]
+    IE_NAME = 'zingmp3:album'
+    IE_DESC = 'mp3.zing.vn albums'
+
+    def _real_extract(self, url):
+        matched = re.match(self._VALID_URL, url)
+        slug = matched.group('slug')
+        album_id = matched.group('album_id')
+
+        webpage = self._download_webpage(
+            'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id)
+        player_xml_url = self._search_regex(
+            r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
+
+        return self._extract_player_xml(
+            player_xml_url, album_id,
+            playlist_title=self._og_search_title(webpage))