qyf 2020-06-12
代理
cookie
验证码的识别
模拟登陆
https://www.baidu.com/s?ie=utf-8&wd=ip
import requests from lxml import etree url = ‘http://www.baidu.com/s?ie=utf-8&wd=ip‘ headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } page_text = requests.get(url=url,headers=headers,proxies={ ‘https‘: "114.98.26.47:4216" }).text with open(‘./ip.html‘,‘w‘,encoding=‘utf-8‘) as fp: fp.write(page_text)
url = "https://www.xicidaili.com/
在xpath表达式中一定不可以出现tbody标签
import requests from lxml import etree url = "https://www.xicidaili.com/nn/%d" headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } ips = [] for page in range(1,30): new_url = format(url%page) page_text = requests.get(new_url,headers=headers).text tree = etree.HTML(page_text) tree_list = tree.xpath(‘//*[@id="ip_list"]//tr‘)[1:] for tr in tree_list: ip = tr.xpath(‘./td[2]/text()‘)[0] ips.append(ip) print(len(ips))
代理池的构建:就是一个列表,列表中存储的是字典,每一个字典存储的键值{‘http‘:‘ip:port‘}
import requests from lxml import etree import random url = "https://www.xicidaili.com/nn/%d" headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } ips = [] for page in range(1,30): new_url = format(url%page) page_text = requests.get(new_url,headers=headers,proxies=random.choice(all_ips)).text tree = etree.HTML(page_text) tree_list = tree.xpath(‘//*[@id="ip_list"]//tr‘)[1:] for tr in tree_list: ip = tr.xpath(‘./td[2]/text()‘)[0] ips.append(ip) print(len(ips))
session = requests.Session() #第一次请求发送:为了捕获cookie且存储到session对象中 headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } first_url = ‘https://xueqiu.com/‘ session.get(first_url,headers=headers) #第二次请求发送:携带着cookie进行请求的发送 url = "https://xueqiu.com/statuses/hot/listV2.json?since_id=-1&max_id=63198&size=15" json_data = session.get(url=url,headers=headers).json() print(json_data)
#!/usr/bin/env python # coding:utf-8 import requests from lxml import etree import requests from hashlib import md5 class Chaojiying_Client(object): def __init__(self, username, password, soft_id): self.username = username password = password.encode(‘utf8‘) self.password = md5(password).hexdigest() self.soft_id = soft_id self.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(‘11111111‘, ‘z12345678‘, ‘905817‘) #用户中心>>软件ID 生成一个替换 96001 # im = open(‘a.jpg‘, ‘rb‘).read() #本地图片文件路径 来替换 a.jpg 有时WIN系统须要// # 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() #封装一个识别码的函数 def transformCode(imgPath,imgType): chaojiying = Chaojiying_Client(‘111111111‘, ‘z12345678‘, ‘905817‘) #用户中心>>软件ID 生成一个替换 96001 im = open(imgPath, ‘rb‘).read() #本地图片文件路径 来替换 a.jpg 有时WIN系统须要// return chaojiying.PostPic(im, imgType)[‘pic_str‘] #1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加() #使用打码平台识别古诗文网中的验证码图片 url = "https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx" headers = { "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } page_text = requests.get(url,headers=headers).text tree = etree.HTML(page_text) code_img_src = "https://so.gushiwen.org"+tree.xpath(‘//*[@id="imgCode"]/@src‘)[0] img_data = requests.get(code_img_src,headers=headers).content with open("./code.jpg",‘wb‘)as fp: fp.write(img_data) print(transformCode(‘./code.jpg‘,1902))
模拟登陆
对点击登录按钮对应的url进行请求发送
动态变化的请求参数:
import requests from lxml import etree from hashlib import md5 class Chaojiying_Client(object): def __init__(self, username, password, soft_id): self.username = username password = password.encode(‘utf8‘) self.password = md5(password).hexdigest() self.soft_id = soft_id self.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() def transformCode(imgPath,imgType): chaojiying = Chaojiying_Client(‘11111111‘, ‘z12345678‘, ‘905817‘) #用户中心>>软件ID 生成一个替换 96001 im = open(imgPath, ‘rb‘).read() #本地图片文件路径 来替换 a.jpg 有时WIN系统须要// return chaojiying.PostPic(im, imgType)[‘pic_str‘] #1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加() #处理cookie headers = { "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" } session = requests.Session() #获取且识别验证码 url = "https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx" page_text = session.get(url,headers=headers).text tree = etree.HTML(page_text) #解析到了验证码图片的地址 code_img_src = "https://so.gushiwen.org"+tree.xpath(‘//*[@id="imgCode"]/@src‘)[0] #解析出模拟登陆请求中动态变化的两个参数的值 __VIEWSTATE = tree.xpath(‘//*[@id="__VIEWSTATE"]/@value‘)[0] __VIEWSTATEGENERATOR = tree.xpath(‘//*[@id="__VIEWSTATEGENERATOR"]/@value‘)[0] #对图片进行请求时捕获cookie img_data = session.get(code_img_src,headers=headers).content with open("./code.jpg",‘wb‘)as fp: fp.write(img_data) #验证码对应的文本数据 code_text = transformCode(‘./code.jpg‘,1902) print(code_text) #对于登录按钮的点击进行请求发送 login_url = "https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx" data = { "__VIEWSTATE":__VIEWSTATE, "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR, "from": "http://so.gushiwen.org/user/collect.aspx", "email": "", "pwd": "z12345678", "code": code_text, "denglu": "登录", } login_page_text=session.post(url=login_url,headers=headers,data=data).text with open(‘./古文.html‘,‘w‘,encoding=‘utf-8‘)as fp: fp.write(login_page_text)