selenium实现企查查自动登录

前言

使用python3.6 selenium包实现用户密码自动登录企查查
编写python函数通过用户名、密码入参返回登录cookie

编写函数

编写get_cookie函数
注意安装chromedriver.exe以及指定chromedriver.exe路径

# -*- coding: utf-8 -*-


from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.chrome.options import Options
from selenium.webdriver import ActionChains
import time
import xlwt
import sys
from tools.tools import *


def get_cookie(username, passwd):
    import importlib  # if python 3.*

    importlib.reload(sys)  # if python 3.*

    # 伪装成浏览器，防止被识破
    option = webdriver.ChromeOptions()
    # option.add_argument('--headless')
    # option.add_argument('--disable-gpu')
    option.add_argument(
        '--user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
        'Chrome/65.0.3325.146 Safari/537.36"')
    driver = webdriver.Chrome(chrome_options=option,
                              executable_path='C:\Program Files (x86)\Google\Chrome\App\chromedriver.exe')
    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
                Object.defineProperty(navigator, 'webdriver', {
                  get: () => undefined
                })
              """
    })

    # 打开登录页面
    driver.get('https://www.qcc.com/user_login')
    # driver.maximize_window()
    # 单击用户名密码登录的标签
    tag = driver.find_element_by_xpath('//*[@id="normalLogin"]')
    tag.click()
    # 将用户名、密码注入
    driver.find_element_by_id('nameNormal').send_keys(username)
    driver.find_element_by_id('pwdNormal').send_keys(passwd)
    time.sleep(2)
    # chrome_options = Options()

    # 开始滑动
    distance = 308
    track = get_track(distance)
    # 按住左键不放
    # action.click_and_hold(source).perform()
    # for i in track:
    #     action.move_by_offset(xoffset=i, yoffset=0).perform()
    #     action.reset_actions()
    i = 0
    while True:
        source = driver.find_element_by_xpath('//*[@id="nc_1_n1z"]')
        action = ActionChains(driver)
        action.reset_actions()
        action.drag_and_drop_by_offset(source, 308, 0)
        # 释放鼠标
        action.release().perform()
        time.sleep(2)
        tip = driver.find_element_by_xpath('//*[@id="dom_id_one"]/div')
        print(tip.text + str(i) + "\n")
        if "验证通过" in tip.text:
            break
        elif i > 10:
            driver.close()
            return "error"
        else:
            driver.find_element_by_xpath('//*[@href="javascript:noCaptcha.reset(1)"]').click()
            i += 1

    time.sleep(2)  # 休眠，人工完成验证步骤，等待程序单击“登录”

    # 单击登录按钮
    btn = driver.find_element_by_xpath('//*[@id="user_login_normal"]/button')
    btn.click()

    cookies = driver.get_cookies()
    cookieStr = ""
    for item in cookies:
        cookieStr += item["name"] + "=" + item["value"] + "; "
    driver.close()
    print("获取cookie成功\n{0}".format(cookieStr))
    return cookieStr

附 tools.py工具函数

在get_cookie中引用get_track(distance)自动滑动验证

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver import ActionChains


def get_track(distance):
    track = []
    current = 0
    mid = distance * 3 / 4
    t = 0.2
    v = 0
    while current < distance:
        if current < mid:
            a = 2
        else:
            a = -3
        v0 = v
        v = v0 + a * t
        move = v0 * t + 1 / 2 * a * t * t
        current += move
        track.append(round(move))
    return track


# 滑动验证码识别
def slide_discern():
    print("滑块验证码验证中。。。") # < br >　　  创建无界面模式
    chrome_options = Options()
    chrome_options.add_argument('--headless')
    chrome_options.add_argument('--disable-gpu')
    driver = webdriver.Chrome(chrome_options=chrome_options) # < br >　　  # 获取到需滑动的按钮
    source = driver.find_element_by_xpath('//*[@id="nc_1_n1z"]')
    action = ActionChains(driver)
    # 按住左键不放
    action.click_and_hold(source).perform()
    # 开始滑动
    distance = 34 # < br >　　  # 模拟以人为速度拖动
    track = get_track(distance)
    for i in track:
        action.move_by_offset(xoffset=i, yoffset=0).perform()
        action.reset_actions()
    # 释放鼠标
    action.release().perform()

使用

if __name__ == "__main__":
    username = "1"
    passwd = "1"
    cook = get_cookie(username, passwd)
    if cook == "error":
        print("success")
    else:
        print("failed")

---

总结

获取企查查登录cookie后，直接通过http请求就能够进行后续想要做的操作了。