shiyu_mj的博客

import requestsfrom lxml import etreeimport reimport threading def spider(link,sub): html1=requests.get(link,headers=headers) k=r'<div class="content" id="content">(?P<contend>.*?)</div>' contend=re.findall(k,html1.tex

1.requsts失败，换了好几个headers都不行，一直418，用的seleniumfrom lxml import etreefrom selenium import webdriverimport timeimport threadingdef dis(itable): for it in itable: print(it)url='https://movie.douban.com/top250'def cal(url): #selenium或取代

# -*- coding: utf-8 -*-"""Created on Thu Jan 6 12:38:42 2022@author: shiyu"""import timeimport requestsfrom lxml import etreeimport reimport threadingimport csvimport pandas as pddef spider(con,dic): url=con[0] print(con[1])

下再webp转为jpgimport requestsimport reimport threadingimport timefrom PIL import Imagefrom io import BytesIOdef dis(iter): for it in iter: print(it)def get(pho_url,i): html=requests.get(pho_url) byte_stream = BytesIO(html.content

一、支持任意章节链接或目录链接# -*- coding: utf-8 -*-"""Created on Thu Jan 6 12:38:42 2022@author: shiyu"""import timeimport requestsfrom lxml import etreeimport redef spider(url): html=requests.get(url,headers=headers) html_=etree.H

import pandas as pdimport reimport json df=pd.read_excel('文化题库.xlsx',sheet_name ='Sheet1')k='[A-Z]'dic={}#清空base.txtwith open('base.txt','w') as f: pass#表格第一行被读取成columns了,所以从1开始for i in range(1,161): line=df.iloc[i] #line[8]有na

# -*- coding: utf-8 -*-"""Created on Sat Jan 8 18:40:55 2022@author: shiyu"""import requestsimport reimport jsonurl='https://www.bilibili.com/video/BV18D4y1c7BM?spm_id_from=333.999.0.0'headers={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64

爬取猫眼电影排名前一百的电影验证问题不知道怎么解决，隔段时间要重新输一次链接‘# -*- coding: utf-8 -*-"""Created on Wed Dec 29 21:07:41 2021@author: shiyu"""import requestsimport re#爬取电影名def get(url): try: html=requests.get(url,headers=headers) except: print(