1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
HEADRequest,
KNOWN_EXTENSIONS,
sanitized_Request,
str_to_int,
urlencode_postdata,
urlhandle_detect_ext,
)
class HearThisAtIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
_PLAYLIST_URL = 'https://hearthis.at/playlist.php'
_TESTS = [{
'url': 'https://hearthis.at/moofi/dr-kreep',
'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
'info_dict': {
'id': '150939',
'ext': 'wav',
'title': 'Moofi - Dr. Kreep',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1421564134,
'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
'upload_date': '20150118',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 71,
'categories': ['Experimental'],
}
}, {
# 'download' link redirects to the original webpage
'url': 'https://hearthis.at/twitchsf/dj-jim-hopkins-totally-bitchin-80s-dance-mix/',
'md5': '5980ceb7c461605d30f1f039df160c6e',
'info_dict': {
'id': '811296',
'ext': 'mp3',
'title': 'TwitchSF - DJ Jim Hopkins - Totally Bitchin\' 80\'s Dance Mix!',
'description': 'Listen to DJ Jim Hopkins - Totally Bitchin\' 80\'s Dance Mix! by TwitchSF on hearthis.at - Dance',
'upload_date': '20160328',
'timestamp': 1459186146,
'thumbnail': 're:^https?://.*\.jpg$',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 4360,
'categories': ['Dance'],
},
}]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
webpage = self._download_webpage(url, display_id)
track_id = self._search_regex(
r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
payload = urlencode_postdata({'tracks[]': track_id})
req = sanitized_Request(self._PLAYLIST_URL, payload)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
track = self._download_json(req, track_id, 'Downloading playlist')[0]
title = '{artist:s} - {title:s}'.format(**track)
categories = None
if track.get('category'):
categories = [track['category']]
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
view_count = str_to_int(self._search_regex(
meta_span % 'plays_count', webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
meta_span % 'likes_count', webpage, 'like count', fatal=False))
comment_count = str_to_int(self._search_regex(
meta_span % 'comment_count', webpage, 'comment count', fatal=False))
duration = str_to_int(self._search_regex(
r'data-length="(\d+)', webpage, 'duration', fatal=False))
timestamp = str_to_int(self._search_regex(
r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
formats = []
mp3_url = self._search_regex(
r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
webpage, 'mp3 URL', fatal=False)
if mp3_url:
formats.append({
'format_id': 'mp3',
'vcodec': 'none',
'acodec': 'mp3',
'url': mp3_url,
})
download_path = self._search_regex(
r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
webpage, 'download URL', default=None)
if download_path:
download_url = compat_urlparse.urljoin(url, download_path)
ext_req = HEADRequest(download_url)
ext_handle = self._request_webpage(
ext_req, display_id, note='Determining extension')
ext = urlhandle_detect_ext(ext_handle)
if ext in KNOWN_EXTENSIONS:
formats.append({
'format_id': 'download',
'vcodec': 'none',
'ext': ext,
'url': download_url,
'preference': 2, # Usually better quality
})
self._sort_formats(formats)
return {
'id': track_id,
'display_id': display_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'comment_count': comment_count,
'like_count': like_count,
'categories': categories,
}
|
