]> asedeno.scripts.mit.edu Git - youtube-dl.git/blob - youtube_dl/extractor/zingmp3.py
Return the item itself if playlist has one entry
[youtube-dl.git] / youtube_dl / extractor / zingmp3.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     ExtractorError,
7     int_or_none,
8 )
9
10
11 class ZingMp3BaseIE(InfoExtractor):
12     _VALID_URL_TMPL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?:%s)/[^/]+/(?P<id>\w+)\.html'
13     _GEO_COUNTRIES = ['VN']
14
15     def _extract_item(self, item, fatal):
16         item_id = item['id']
17         title = item.get('name') or item['title']
18
19         formats = []
20         for k, v in (item.get('source') or {}).items():
21             if not v:
22                 continue
23             if k in ('mp4', 'hls'):
24                 for res, video_url in v.items():
25                     if not video_url:
26                         continue
27                     if k == 'hls':
28                         formats.extend(self._extract_m3u8_formats(
29                             video_url, item_id, 'mp4',
30                             'm3u8_native', m3u8_id=k, fatal=False))
31                     elif k == 'mp4':
32                         formats.append({
33                             'format_id': 'mp4-' + res,
34                             'url': video_url,
35                             'height': int_or_none(self._search_regex(
36                                 r'^(\d+)p', res, 'resolution', default=None)),
37                         })
38             else:
39                 formats.append({
40                     'ext': 'mp3',
41                     'format_id': k,
42                     'tbr': int_or_none(k),
43                     'url': self._proto_relative_url(v),
44                     'vcodec': 'none',
45                 })
46         if not formats:
47             if not fatal:
48                 return
49             msg = item['msg']
50             if msg == 'Sorry, this content is not available in your country.':
51                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
52             raise ExtractorError(msg, expected=True)
53         self._sort_formats(formats)
54
55         subtitles = None
56         lyric = item.get('lyric')
57         if lyric:
58             subtitles = {
59                 'origin': [{
60                     'url': lyric,
61                 }],
62             }
63
64         album = item.get('album') or {}
65
66         return {
67             'id': item_id,
68             'title': title,
69             'formats': formats,
70             'thumbnail': item.get('thumbnail'),
71             'subtitles': subtitles,
72             'duration': int_or_none(item.get('duration')),
73             'track': title,
74             'artist': item.get('artists_names'),
75             'album': album.get('name') or album.get('title'),
76             'album_artist': album.get('artists_names'),
77         }
78
79     def _real_extract(self, url):
80         page_id = self._match_id(url)
81         webpage = self._download_webpage(
82             url.replace('://zingmp3.vn/', '://mp3.zing.vn/'),
83             page_id, query={'play_song': 1})
84         data_path = self._search_regex(
85             r'data-xml="([^"]+)', webpage, 'data path')
86         return self._process_data(self._download_json(
87             'https://mp3.zing.vn/xhr' + data_path, page_id)['data'])
88
89
90 class ZingMp3IE(ZingMp3BaseIE):
91     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip'
92     _TESTS = [{
93         'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
94         'md5': 'ead7ae13693b3205cbc89536a077daed',
95         'info_dict': {
96             'id': 'ZWZB9WAB',
97             'title': 'Xa Mãi Xa',
98             'ext': 'mp3',
99             'thumbnail': r're:^https?://.+\.jpg',
100             'subtitles': {
101                 'origin': [{
102                     'ext': 'lrc',
103                 }]
104             },
105             'duration': 255,
106             'track': 'Xa Mãi Xa',
107             'artist': 'Bảo Thy',
108             'album': 'Special Album',
109             'album_artist': 'Bảo Thy',
110         },
111     }, {
112         'url': 'https://mp3.zing.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
113         'md5': 'e9c972b693aa88301ef981c8151c4343',
114         'info_dict': {
115             'id': 'ZO8ZF7C7',
116             'title': 'Sương Hoa Đưa Lối',
117             'ext': 'mp4',
118             'thumbnail': r're:^https?://.+\.jpg',
119             'duration': 207,
120             'track': 'Sương Hoa Đưa Lối',
121             'artist': 'K-ICM, RYO',
122         },
123     }, {
124         'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
125         'only_matching': True,
126     }]
127     IE_NAME = 'zingmp3'
128     IE_DESC = 'mp3.zing.vn'
129
130     def _process_data(self, data):
131         return self._extract_item(data, True)
132
133
134 class ZingMp3AlbumIE(ZingMp3BaseIE):
135     _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
136     _TESTS = [{
137         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
138         'info_dict': {
139             '_type': 'playlist',
140             'id': 'ZWZBWDAF',
141             'title': 'Lâu Đài Tình Ái',
142         },
143         'playlist_count': 10,
144     }, {
145         'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
146         'only_matching': True,
147     }, {
148         'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
149         'only_matching': True,
150     }]
151     IE_NAME = 'zingmp3:album'
152
153     def _process_data(self, data):
154         def entries():
155             for item in (data.get('items') or []):
156                 entry = self._extract_item(item, False)
157                 if entry:
158                     yield entry
159         info = data.get('info') or {}
160         return self.playlist_result(
161             entries(), info.get('id'), info.get('name') or info.get('title'))