考试宝-网络题库爬虫python实现

from time import sleep
from selenium import webdriver
from selenium.webdriver.common.by import By
import xlwt
import time

driver = webdriver.Chrome()  # 谷歌浏览器
driver.get('https://www.zaixiankaoshi.com/online/?paperId=4940184&practice=&modal=1&is_recite=&qtype=&text=%E9%A1%BA%E5%BA%8F%E7%BB%83%E4%B9%A0&sequence=0&is_collect=0')
driver.implicitly_wait(50)
driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[2]/div[2]/div[1]/p[2]/span[2]/div').click()

work_book = xlwt.Workbook(encoding="UTF-8")
work_sheet = work_book.add_sheet("sheet1")

for i in range(439):
    time.sleep(1)
    all=[]
    # 定位元素并提取内容
    answer = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[2]/div[1]/div/div[1]/div/b/span').text
    title = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[1]/div/div[1]/div/div').text
    part_A = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[1]/div/div[2]/div/div[1]/span[2]').text
    part_B = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[1]/div/div[2]/div/div[2]/span[2]').text
    part_C = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[1]/div/div[2]/div/div[3]/span[2]').text
    part_D = driver.find_element(By.XPATH,'//*[@id="body"]/div[2]/div[1]/div[2]/div[1]/div/div[1]/div/div[2]/div/div[4]/span[2]').text

    # 对内容个性化处理
    title=str(i+1)+"."+title
    part_A = "A." + part_A
    part_B = "B." + part_B
    part_C = "C." + part_C
    part_D = "D." + part_D
    answer="答案:"+answer
    all.append(title)
    all.append(part_A)
    all.append(part_B)
    all.append(part_C)
    all.append(part_D)
    all.append(answer)
    # 分别写入excel表格中
    for ii in range(6):
        work_sheet.write(i,ii,all[ii]) # 行 列 内容
    # 第1条数据 最大化窗口
    if i==0:
        driver.maximize_window()
        time.sleep(2)
    # 点击下一条
    driver.find_element(By.CLASS_NAME,'el-button--primary').click()
    # 对第10条数据取消收藏处理
    if i==9:
        driver.find_element(By.XPATH,'/html/body/div[4]/div/div[3]/button[1]').click()
# 存储表格
work_book.save("tt5.xlsx")
# 退出浏览器
driver.quit()

你可能感兴趣的:(python基础学习,python,爬虫,chrome)