import requests
from hashlib import md5
class Chaojiying_Client(object):def __init__(self, username, password, soft_id):self.username = usernamepassword =  password.encode('utf8')self.password = md5(password).hexdigest()self.soft_id = soft_idself.base_params = {'user': self.username,'pass2': self.password,'softid': self.soft_id,}self.headers = {'Connection': 'Keep-Alive','User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',}def PostPic(self, im, codetype):"""
        im: 图片字节codetype: 题目类型 参考 http://www.chaojiying.com/price.html"""
        params = {'codetype': codetype,}params.update(self.base_params)files = {'userfile': ('ccc.jpg', im)}r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)return r.json()def ReportError(self, im_id):"""
        im_id:报错题目的图片ID"""
        params = {'id': im_id,}params.update(self.base_params)r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)return r.json()if __name__ == '__main__':chaojiying = Chaojiying_Client('用户名', '密码', '软件ID')    #用户中心>>软件ID 生成一个替换 im = open('a.jpg', 'rb').read()                             #本地图片文件路径 来替换 a.jpg     print(chaojiying.PostPic(im, 1902))                         #1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()

def get_codeImg_text(imgPath,imgType):chaojiying = Chaojiying_Client('用户名', '密码', '软甲ID')    #用户中心>>软件ID 生成一个替换im = open(imgPath, 'rb').read()#本地图片文件路径 来替换 a.jpg return chaojiying.PostPic(im, imgType)['pic_str']

import requests
from lxml import etree#前期准备工作
session = requests.Session()
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.64 Safari/537.36",
}#两个url指向一样只是方便区分所以写了两个
url = "https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx"
login_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'#请求登陆页面并且将登陆页面放到实例化的tree里
page_text = requests.session(url=url,headers=headers).text
tree = etree.HTML(page_text)#解析验证码图片保存到本地
code_img_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0]
code_img_data = requests.session(url=code_img_src,headers=headers).content #直接获取二进制流
with open("./code.jpg","wb") as f:f.write(code_img_data)#解析动态参数，动态参数往往都会隐藏在前台页面中
__VIEWSTATE = tree.xpath('//input[@id="__VIEWSTATE"]/@value')[0]
__VIEWSTATEGENERATOR = tree.xpath('//input[@id="__VIEWSTATEGENERATOR"]/@value')[0]#使用打码平台识别出来的验证码图片数据
codeImg_text = get_codeImg_text("./code.jpg",1902)#整合所需要的数据
data = {#处理了动态参数"__VIEWSTATE": __VIEWSTATE,"__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,"from": "http://so.gushiwen.org/user/collect.aspx","email": "www.zhangbowudi@qq.com","pwd": "bobo328410948","code": codeImg_text,"denglu": "登录",
}#模拟登陆并把页面写入本地
page_text = requests.session(url=login_url,headers=headers,data=data).text
with open("./login.html","w",encoding="utf-8") as f:f.write(page_text)

url = "https://www.baidu.com/s?ie=UTF-8&wd=ip"
page_text = requests.get(url=url,headers=headers,proxies={"类型":"ip:端口号"}).textwith open("./ip.html",'w',encoding="utf-8") as f:f.write(page_text)

使用模块：
#导包
from multiprocessing.dummy import Pool
#实例化
pool = Pool(4)#线程数
pool.map(func,iterable,chunksize=None)可以基于异步实现：让参数1（func）对应的函数对参数2（iterable）对应的容器元素依次进行操作（基于异步的操作）

import time
pool = Pool(4)
def func(url):print("正在请求:",url)time.sleep(2)print("请求完毕:",url)urls = ["www.1.com","www.2.com","www.3.com","www.4.com",
]   start = time.time()
for url in urls:func(url)
print(time.time()-start)start2 = time.time()
pool.map(fun,urls)
print(time.time()-start2)