winter_dong的博客

import urllib.requestimport urllib.parseimport osdef create_request(barname,page,base_url): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chro...

import urllib.requestimport urllib.parse"""request 封装 对url的高级定制opener封装 对请求过程的高级定制 urllib.request.urlopen()opener封装需要依赖于一个handler对象handle是一个类，提供HTTPHandle\HTTPCookieProcesser\HTTPProxyHandler...

import urllib.requestimport urllib.parse# 配置代理对象，把协议作为键，主机和端口号为值handler = urllib.request.ProxyHandler(proxies={'http':'ip:端口'})url = 'https://www.baidu.com/s?wd=ip'headers = { 'User-Agent':...

# coding:utf-8import timefrom selenium import webdriverfrom selenium.webdriver.common.keys import Keysoption = webdriver.ChromeOptions()mobile_emulation = {"deviceName":"iPhone X"}option.add_e...

import requestsfrom bs4 import BeautifulSoupimport timeimport csvimport datetime# 得到当前的时间nowTime = datetime.datetime.now().strftime('%Y-%m-%d %H-%M-%S')# 创建列表储存新闻标题new_title = []# 创建列表储存新闻跳...

import redisfrom scrapy.exceptions import NotConfiguredclass RandomProxyMiddleware(object): """ 利用scrapy本身的proxy middle机制，实现一个随机IP代理池，并且可以动态的删除有问题的IP """ def __init__(self, setti...

import tesserocrfrom PIL import Image# 1.识别验证码image = Image.open('code.jpg')# result = tesserocr.image_to_text(image)# print(result)# 2.直接将图片文件转换为字符串# print(tesserocr.file_to_text('code.jpg')...

import pymysqlfrom selenium import webdriverfrom selenium.common.exceptions import TimeoutExceptionfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support import expected_condi...

链接：https://www.cnblogs.com/c-x-a/p/10334624.html