Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hearthisat.py

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