From aae4df73fae2dd0d8788dbd2e8f491fd90d9447c Mon Sep 17 00:00:00 2001 From: lededev Date: Tue, 19 Oct 2021 01:00:50 +0800 Subject: [PATCH] =?UTF-8?q?javbus.py:=20=E6=B8=85=E7=90=86=E8=BF=87?= =?UTF-8?q?=E6=9C=9F=E4=BB=A3=E7=A0=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- WebCrawler/javbus.py | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/WebCrawler/javbus.py b/WebCrawler/javbus.py index 63457bf..7866052 100644 --- a/WebCrawler/javbus.py +++ b/WebCrawler/javbus.py @@ -5,7 +5,6 @@ from lxml import etree#need install import json from ADC_function import * from WebCrawler.storyline import getStoryline -import inspect def getActorPhoto(html): actors = html.xpath('//div[@class="star-name"]/a') @@ -60,17 +59,6 @@ def getCID(html): string = html.xpath("//a[contains(@class,'sample-box')][1]/@href")[0].replace('https://pics.dmm.co.jp/digital/video/','') result = re.sub('/.*?.jpg','',string) return result -def getOutline0(number): #获取剧情介绍 airav.wiki站点404,函数暂时更名,等无法恢复时删除 - if any(caller for caller in inspect.stack() if os.path.basename(caller.filename) == 'airav.py'): - return '' # 从airav.py过来的调用不计算outline直接返回,避免重复抓取数据拖慢处理速度 - try: - htmlcode = get_html('https://cn.airav.wiki/video/' + number) - from WebCrawler.airav import getOutline as airav_getOutline - result = airav_getOutline(htmlcode) - return result - except: - pass - return '' def getOutline(number, title): #获取剧情介绍 多进程并发查询 return getStoryline(number,title) def getSeriseJa(html):