aimer1111
2022-06-15 16:41
采纳率: 100%
浏览 49

selenium模拟登陆+爬取数据

from selenium import webdriver
from time import sleep
from selenium.webdriver.common.by import By
from lxml import etree
import requests
import time
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36'}

driver = webdriver.Chrome()
driver.get('https://www.timeshighereducation.com/')
sleep(5)

driver.find_element(By.XPATH,'//div[@class="col-sm-12"]/div[@class="navbar-button__wrapper"]/ul/li/a[@title="User account"]').click()
sleep(5)
driver.find_element(By.XPATH,'//div[@class="region region-secondary-navigation"]/section/div/ul/li/a[@id="modal-login"]').click()
sleep(5)

sleep(5)
driver.switch_to.frame(driver.find_element(By.XPATH,'//div[@id="modal-content"]/iframe'))

driver.find_element(ByXPATH,'//input[@placeholder="Username or email"]').send_keys("123456")
driver.find_element(By.XPATH,'//input[@placeholder="Password"]').send_keys("123456")
# driver.refresh()
driver.find_element(By.XPATH,'//form[@class="user-login-form"]/div/input[@value="Log in"]').click()
sleep(5)
driver.switch_to.parent_frame
sleep(5)

解析html字符串,获取需要的信息

def parse_html(html):
text = etree.HTML(html)

node_list = text.xpath('//tbody/tr[@class="odd row-1 js-row"]')
# print(node_list)
for i in node_list:
    try:
        # rank
        rank = i.xpath('/td[@class="rank sorting_1 sorting_2"]/text()')
        # name
        name = i.xpath('/td[@class=" name namesearch"]/a/text()')
        # region
        region = i.xpath('/td/div/div[@class="location"]/span/a/text()')
        #ratio
        # ratio = i.xpath('')
        # 构建json格式的字符串
        items = {
            "排名": rank,
            "名称": name,
            "地区/国家": region
        }
        print(items)
    except:
        pass

def main():
# 循环获取第0~15的网页源码,并解析
for page in range(0, 16):
# 每个网页的网址
url = 'https://www.timeshighereducation.com/world-university-rankings/2022#!/page/'+ str(page) + '/length/25/sort_by/rank/sort_order/asc/cols/stats'
# 爬取网页源码
html = requests.get(url, headers=headers).text
# 解析网页信息
parse_html(html)

程序运行入口

if name == 'main':
main()

为什么我爬不到数据,有没有能人赐教,本人初次接触

2条回答 默认 最新

相关推荐 更多相似问题