From 4da4516973b56bcaa65794a8ae0856cf54740c54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Fri, 30 Sep 2016 19:59:08 +0200 Subject: [PATCH] [byutv] Rely on _match_id and _parse_json --- youtube_dl/extractor/byutv.py | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 3aec601f8..b2d25eec0 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor @@ -8,7 +7,7 @@ from ..utils import ExtractorError class BYUtvIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P[^/?#]+)' + _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P[^/?#]+)' _TEST = { 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', 'md5': '05850eb8c749e2ee05ad5a1c34668493', @@ -27,15 +26,15 @@ class BYUtvIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) episode_code = self._search_regex( r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information') - episode_json = re.sub( - r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code) - ep = json.loads(episode_json) + + ep = self._parse_json( + episode_code, video_id, transform_source=lambda s: + re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s)) if ep['providerType'] == 'Ooyala': return {