From 8e2ec95575fc8157da1ec3ec408737f200aa44d7 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 11 Jan 2015 23:40:27 +0100 Subject: [PATCH] [drbonanza] Simplify and fix duration (#4687) --- youtube_dl/extractor/drbonanza.py | 79 ++++++++++++++++++------------- 1 file changed, 45 insertions(+), 34 deletions(-) diff --git a/youtube_dl/extractor/drbonanza.py b/youtube_dl/extractor/drbonanza.py index 8cbdb57b3..7626219ba 100644 --- a/youtube_dl/extractor/drbonanza.py +++ b/youtube_dl/extractor/drbonanza.py @@ -1,11 +1,15 @@ from __future__ import unicode_literals -from .common import InfoExtractor -from .common import ExtractorError -from ..utils import parse_iso8601 import json import re +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) + + class DRBonanzaIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P\d+))?(?:[#&]|$)' @@ -17,11 +21,12 @@ class DRBonanzaIE(InfoExtractor): 'ext': 'mp4', 'title': 'Talkshowet - Leonard Cohen', 'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', 'timestamp': 1295537932, 'upload_date': '20110120', - 'duration': 3664000, + 'duration': 3664, }, - },{ + }, { 'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410', 'md5': '6dfe039417e76795fb783c52da3de11d', 'info_dict': { @@ -29,37 +34,47 @@ class DRBonanzaIE(InfoExtractor): 'ext': 'mp3', 'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission', 'description': 'md5:501e5a195749480552e214fbbed16c4e', + 'thumbnail': 're:^https?://.*\.(?:gif|jpg)$', 'timestamp': 1223274900, 'upload_date': '20081006', - 'duration': 7369000, + 'duration': 7369, }, }] def _real_extract(self, url): url_id = self._match_id(url) - - webpage = self._download_webpage(url, url_id if url_id else "") - + webpage = self._download_webpage(url, url_id) + if url_id: - info = json.loads(self._html_search_regex(r'({.*?' + url_id + '.*})', webpage, 'json')) + info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json')) else: # Just fetch the first video on that page info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json')) - + asset_id = str(info['AssetId']) title = info['Title'].rstrip(' \'\"-,.:;!?') - duration = info['Duration'] - timestamp = parse_iso8601(re.sub(r'\.\d+$', '', info['Created'])) # First published online. "FirstPublished" contains the date for original airing. - + duration = int_or_none(info.get('Duration'), scale=1000) + # First published online. "FirstPublished" contains the date for original airing. + timestamp = parse_iso8601( + re.sub(r'\.\d+$', '', info['Created'])) + def parse_filename_info(url): match = re.search(r'/\d+_(?P\d+)x(?P\d+)x(?P\d+)K\.(?P\w+)$', url) if match: - return {'width': int(match.group(1)), 'height': int(match.group(2)), 'bitrate': int(match.group(3)), 'ext': match.group(4)} + return { + 'width': int(match.group('width')), + 'height': int(match.group('height')), + 'vbr': int(match.group('bitrate')), + 'ext': match.group('ext') + } match = re.search(r'/\d+_(?P\d+)K\.(?P\w+)$', url) if match: - return {'bitrate': int(match.group(1)), 'ext': match.group(2)} - return {'width': None, 'height': None, 'bitrate': None, 'ext': None} - + return { + 'vbr': int(match.group('bitrate')), + 'ext': match.group(2) + } + return {} + video_types = ['VideoHigh', 'VideoMid', 'VideoLow'] preferencemap = { 'VideoHigh': -1, @@ -67,47 +82,43 @@ class DRBonanzaIE(InfoExtractor): 'VideoLow': -3, 'Audio': -4, } - + formats = [] for file in info['Files']: if info['Type'] == "Video": if file['Type'] in video_types: - fileinfo = parse_filename_info(file['Location']) - formats.append({ + format = parse_filename_info(file['Location']) + format.update({ 'url': file['Location'], 'format_id': file['Type'].replace('Video', ''), 'preference': preferencemap.get(file['Type'], -10), - 'width': fileinfo['width'], - 'height': fileinfo['height'], - 'vbr': fileinfo['bitrate'], - 'ext': fileinfo['ext'], }) + formats.append(format) elif file['Type'] == "Thumb": thumbnail = file['Location'] elif info['Type'] == "Audio": if file['Type'] == "Audio": - fileinfo = parse_filename_info(file['Location']) - formats.append({ + format = parse_filename_info(file['Location']) + format.update({ 'url': file['Location'], 'format_id': file['Type'], - 'abr': fileinfo['bitrate'], - 'ext': fileinfo['ext'], 'vcodec': 'none', }) + formats.append(format) elif file['Type'] == "Thumb": thumbnail = file['Location'] - - description = "{}\n{}\n{}\n".format(info['Description'], info['Actors'], info['Colophon']) + + description = '%s\n%s\n%s\n' % ( + info['Description'], info['Actors'], info['Colophon']) for f in formats: f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/') f['url'] = f['url'].replace('mp4:bonanza', 'bonanza') - self._sort_formats(formats) - + display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id display_id = re.sub(r'-+', '-', display_id) - + return { 'id': asset_id, 'display_id': display_id, -- 2.22.2