From 0afddd0b9ae23e32d809e2f4edd5574e28d28487 Mon Sep 17 00:00:00 2001
From: wangchangren <changren.wcr@alibaba-inc.com>
Date: Sat, 18 Jun 2022 08:56:44 +0800
Subject: [PATCH] fix: refactor two extractors into one
---
youtube_dl/extractor/extractors.py | 5 +--
youtube_dl/extractor/qingting.py | 71 ++++++++++++------------------
2 files changed, 30 insertions(+), 46 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 9bb23ecc4..7512bef7f 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -975,10 +975,7 @@ from .presstv import PressTVIE
from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE
from .pyvideo import PyvideoIE
-from .qingting import (
- QingTingMobileIE,
- QingTingDeskTopIE,
-)
+from .qingting import QingTingIE
from .qqmusic import (
QQMusicIE,
QQMusicSingerIE,
diff --git a/youtube_dl/extractor/qingting.py b/youtube_dl/extractor/qingting.py
index 86a59d3ba..65a49904d 100644
--- a/youtube_dl/extractor/qingting.py
+++ b/youtube_dl/extractor/qingting.py
@@ -1,46 +1,17 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from youtube_dl import utils
-class QingTingMobileIE(InfoExtractor):
- IE_NAME = 'QingTing'
- _VALID_URL = r'(?:https?://)?(?:www\.)?m\.(?:qingting\.fm|qtfm\.cn)/vchannels/\d+/programs/(?P<id>\d+)'
- _TEST = {
- 'url': 'https://m.qingting.fm/vchannels/378005/programs/22257411/',
- 'md5': '47e6a94f4e621ed832c316fd1888fb3c',
- 'info_dict': {
- 'id': '22257411',
- 'ext': 'mp3',
- 'title': '用了十年才修改，谁在乎教科书？-睡前消息-蜻蜓FM听头条',
- }
- }
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(r'(?s)<title\b[^>]*>(.*)</title>', webpage, 'title', default=None) or self._og_search_title(webpage)
- url = self._search_regex(
- r'''("|')audioUrl\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
- webpage, 'audio URL', group="url")
- test_url = utils.url_or_none(url)
- if not test_url:
- raise utils.ExtractorError('Invalid audio URL %s' % (url,))
- url = test_url
- return {
- 'id': video_id,
- 'title': title,
- 'ext': 'mp3',
- 'url': url,
- }
-
-class QingTingDeskTopIE(InfoExtractor):
+class QingTingIE(InfoExtractor):
IE_NAME = 'QingTing'
- _VALID_URL = r'(?:https?://)?(?:www\.)?(?:qingting\.fm|qtfm\.cn)/channels/\d+/programs/(?P<id>\d+)'
+ _VALID_URL = r'''(?x)
+ (?:https?://)?(?:www\.)?
+ (?P<m>m\.)?(?:qingting\.fm|qtfm\.cn)/(?(m)v|)
+ channels/\d+/programs/(?P<id>\d+)'''
_TEST = {
'url': 'https://www.qingting.fm/channels/378005/programs/22257411/',
'md5': '47e6a94f4e621ed832c316fd1888fb3c',
@@ -56,11 +27,27 @@ class QingTingDeskTopIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'(?s)<title\b[^>]*>(.*)</title>', webpage, 'title',
default=None) or self._og_search_title(webpage)
- url = self._search_regex(
- r'''("|')alternate\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
- webpage, 'alternate URL', group="url")
- test_url = utils.url_or_none(url)
- if not test_url:
- raise utils.ExtractorError('Invalid audio URL %s' % (url,))
- url = test_url
- return self.url_result(url=url, video_id=video_id, video_title=title)
+ urlType = self._search_regex(
+ self._VALID_URL,
+ url, 'audio URL', group="m")
+ if urlType == 'm.':
+ url = self._search_regex(
+ r'''("|')audioUrl\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
+ webpage, 'audio URL', group="url")
+ test_url = utils.url_or_none(url)
+ if not test_url:
+ raise utils.ExtractorError('Invalid audio URL %s' % (url,))
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'ext': 'mp3',
+ 'url': test_url,
+ }
+ else:
+ url = self._search_regex(
+ r'''("|')alternate\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
+ webpage, 'alternate URL', group="url")
+ test_url = utils.url_or_none(url)
+ if not test_url:
+ raise utils.ExtractorError('Invalid audio URL %s' % (url,))
+ return self.url_result(url=test_url, video_id=video_id, video_title=title)