diff options
Diffstat (limited to 'youtube_dl/extractor/hearthisat.py')
| -rw-r--r-- | youtube_dl/extractor/hearthisat.py | 135 |
1 files changed, 0 insertions, 135 deletions
diff --git a/youtube_dl/extractor/hearthisat.py b/youtube_dl/extractor/hearthisat.py deleted file mode 100644 index 18c252012..000000000 --- a/youtube_dl/extractor/hearthisat.py +++ /dev/null @@ -1,135 +0,0 @@ -# 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\-]+)/?$' - _PLAYLIST_URL = 'https://hearthis.at/playlist.php' - _TESTS = [{ - 'url': 'https://hearthis.at/moofi/dr-kreep', - 'md5': 'ab6ec33c8fed6556029337c7885eb4e0', - 'info_dict': { - 'id': '150939', - 'ext': 'wav', - 'title': 'Moofi - Dr. Kreep', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1421564134, - 'description': 'Listen to Dr. Kreep by Moofi on hearthis.at - Modular, Eurorack, Mutable Intruments Braids, Valhalla-DSP', - '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': r'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, - } |