python網路爬蟲之模擬登入 自動獲取cookie值 驗證碼識別的具體實現

import requests

headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36",
        #手動處理cookie
        # "Cookie": "acw_tc=2760820816186635434807019e3f39e1bf4a8a9b9ad20b50586fb6c8184f56; xq_a_token=520e7bca78673752ed71e19b8820b5eb854123af; xqat=520e7bca78673752ed71e19b8820b5eb854123af; xq_r_token=598dda88240ff69f663261a3bf4ca3d9f9700cc0; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTYyMTIxOTc0OSwiY3RtIjoxNjE4NjYzNTE1MDI1LCJjaWQiOiJkOWQwbjRBWnVwIn0.BGdEgnctB-rv0Xiu8TxrBEshPF4w0StKOE5jKTxy8OFz_pLwNl5VK9v2e8jyU4jaQt9xZTvgsPiYYbiIgmUUpPkamuT0pITHOFoNoKFYFz0syxQMuuAa93pPvSJxeCutqod4cvdWt6f4iRjtHyjAY0zVrv3xLi2ksc9noSf9sH3eLVu9Yjr3PzbF1QDzbXyQsX7oS5Y5Iwt2p-XartCGMlKWzWz9TPiFc3oZ6o7CMWu7Tvfb5D2XGlIU6L8wlPBMwoz2Zdy_zQif9itUqoBvQjNIa3E6UYag-vlY7nNFSDJh0UCobapBjdNITBVVvwFtYn6C-R16y6O8S5iko4E59g; u=461618663543485; Hm_lvt_1db88642e346389874251b5a1eded6e3=1618663545; device_id=24700f9f1986800ab4fcc880530dd0ed; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1618664825"
    }
session = requests.Session() # 建立session物件
# 第一次使用session，捕獲請求cookie
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
page_text = session.get(url = url,headers = headers).text
# 解析驗證碼圖片地址
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.cn/' + tree.xpath('//*[@id="imgCode"]/@src')[0]
# 將驗證碼圖片儲存到本地
img_data = session.get(img_src,headers = headers).content
with open('./code.jpg','wb') as fp:
    fp.write(img_data)

#!/usr/bin/env python
# coding:utf-8

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: 圖片位元組
        codetype: 題目型別 參考 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:報錯題目的圖片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('超級鷹使用者名稱', '超級鷹使用者名稱的密碼', '96001')	#使用者中心>>軟體ID 生成一個替換 96001
    im = open('a.jpg', 'rb').read()													#本地圖片檔案路徑 來替換 a.jpg 有時WIN系統須要//
    print(chaojiying.PostPic(im, 1902))												#1902 驗證碼型別  官方網站>>價格體系 3.4+版 print 後要加()

# 模擬登入
# 流程：1 對點選登入按鈕對應的請求進行傳送（post請求）
#      2 處理請求引數：
#        使用者名稱 密碼 驗證碼 其他防偽引數
import requests
from lxml import etree
from chaojiying_Python.chaojiying import Chaojiying_Client

headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36",
}
# 封裝好的驗證碼識別函數
def tranformImgCode(imgPath,imgType):
    chaojiying = Chaojiying_Client('使用者名稱', '密碼', '軟體ID')	        # 使用者中心>>軟體ID 生成一個替換 軟體ID
    im = open(imgPath, 'rb').read()													#本地圖片檔案路徑 來替換 a.jpg 有時WIN系統須要//
    return(chaojiying.PostPic(im, imgType))['pic_str']

# 自動獲取cookie
session = requests.Session()

# 識別驗證碼
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
page_text = session.get(url = url,headers = headers).text
# 解析驗證碼圖片地址
tree = etree.HTML(page_text)
img_src = 'https://so.gushiwen.cn/' + tree.xpath('//*[@id="imgCode"]/@src')[0]
# 將驗證碼圖片儲存到本地
img_data = session.get(img_src,headers = headers).content
with open('./code.jpg','wb') as fp:
    fp.write(img_data)

# 識別驗證碼
code_text = tranformImgCode('./code.jpg',1902)
print(code_text)

login_url = 'https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'
data = {
    '__VIEWSTATE': 'frn5Bnnr5HRYCoJJ9fIlFFjsta310405ClDr+hy0/V9dyMGgBf34A2YjI8iCAaXHZarltdz1LPU8hGWIAUP9y5eLjxKeYaJxouGAa4YcCPC+qLQstMsdpWvKGjg=',
    '__VIEWSTATEGENERATOR': 'C93BE1AE',
    'from': 'http://so.gushiwen.cn/user/collect.aspx',
    'email': '使用者名稱', # 更換自己的使用者名稱
    'pwd': '密碼',     # 更換自己的密碼
    'code': code_text,
    'denglu': '登入'
}
# 對點選登入按鈕發起請求,獲取登入成功後對應的頁面原始碼資料
page_text_login = session.post(url = login_url,data = data,headers = headers).text

with open('./gushiwen.html','w',encoding = 'utf-8') as fp:
    fp.write(page_text_login)