_ Git - youtube-dl/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_urllib_request
   8 from ..utils import (
   9     str_to_int,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class HearThisAtIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
  16     _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
  17     _TEST = {
  18         'url': 'https://hearthis.at/moofi/dr-kreep',
  19         'md5': 'd594c573227a89f4256f0b03e68c80cc',
  20         'info_dict': {
  21             'id': '150939',
  22             'ext': 'mp3',
  23             'title': 'Moofi - Dr. Kreep',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'timestamp': 1421564134,
  26             'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
  27             'upload_date': '20150118',
  28             'comment_count': int,
  29             'view_count': int,
  30             'like_count': int,
  31             'duration': 71,
  32             'categories': ['Experimental'],
  33         }
  34     }
  35
  36     def _real_extract(self, url):
  37         m = re.match(self._VALID_URL, url)
  38         display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
  39
  40         webpage = self._download_webpage(url, display_id)
  41         track_id = self._search_regex(
  42             r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
  43
  44         payload = urlencode_postdata({'tracks[]': track_id})
  45         req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
  46         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  47
  48         track = self._download_json(req, track_id, 'Downloading playlist')[0]
  49         title = '{artist:s} - {title:s}'.format(**track)
  50
  51         categories = None
  52         if track.get('category'):
  53             categories = [track['category']]
  54
  55         description = self._og_search_description(webpage)
  56         thumbnail = self._og_search_thumbnail(webpage)
  57
  58         meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
  59         view_count = str_to_int(self._search_regex(
  60             meta_span % 'plays_count', webpage, 'view count', fatal=False))
  61         like_count = str_to_int(self._search_regex(
  62             meta_span % 'likes_count', webpage, 'like count', fatal=False))
  63         comment_count = str_to_int(self._search_regex(
  64             meta_span % 'comment_count', webpage, 'comment count', fatal=False))
  65         duration = str_to_int(self._search_regex(
  66             r'data-length="(\d+)', webpage, 'duration', fatal=False))
  67         timestamp = str_to_int(self._search_regex(
  68             r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
  69
  70         track_url = self._search_regex(
  71             r'<a[^>]+data-mp3="([^"]+)"', webpage, 'track URL')
  72
  73         formats = [{
  74             'format_id': 'mp3',
  75             'url': track_url,
  76             'vcodec': 'none',
  77         }]
  78
  79         return {
  80             'id': track_id,
  81             'display-id': display_id,
  82             'title': title,
  83             'formats': formats,
  84             'thumbnail': thumbnail,
  85             'description': description,
  86             'duration': duration,
  87             'timestamp': timestamp,
  88             'view_count': view_count,
  89             'comment_count': comment_count,
  90             'like_count': like_count,
  91             'categories': categories,
  92         }