首先打开搜索界面，然后打开检查
    image.png
    res=browser.find_elements_by_class_name(‘result’)抓取页面的内容
    image.png
    x=browser.find_element_by_id(‘page’)
    image.png
    然后抓取page里面的a标签，links=x.find_elements_by_tag_name(‘a’)
    然后for循环，赋值给a for a in links:
    if page_num in a.get_attribute(‘href’):
    image.png

    百度采集

    1. from selenium import webdriver
    2. from selenium.webdriver.common.keys import Keys
    3. from time import sleep
    4. import requests
    5. headers = {
    6.     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    7.     'Accept-Encoding': 'gzip, deflate, compress',
    8.     'Accept-Language': 'en-us;q=0.5,en;q=0.3',
    9.     'Cache-Control': 'max-age=0',
    10.     'Connection': 'keep-alive',
    11.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36'
    12. }
    13. def baidu_url():
    14.     browser=webdriver.Chrome()
    15.     browser.get('https://www.baidu.com')
    16.     browser.find_element_by_id('kw').send_keys('inurl:asp?id=')
    17.     browser.find_element_by_id('kw').send_keys(Keys.ENTER)
    18.     pn=0
    19.     for p in range(10,1000,10):
    20.         page_num='&pn='+str(p)
    21.         sleep(5)
    22.         res=browser.find_elements_by_class_name('result')
    23.         zhuqu(res)
    24.         x=browser.find_element_by_id('page')
    25.         links=x.find_elements_by_tag_name('a')
    26.         for a in links:
    27.             if page_num in a.get_attribute('href'):
    28.                 a.click()
    29.                 break
    30.         print('当前抓取第%s 页内容' % int(p / 10+1))
    31. def zhuqu(res):
    32.     for re in res:
    33.         f=open('d:/baidu_url.txt','a')
    34.         t=re.find_element_by_tag_name('a').text
    35.         zu=re.find_element_by_tag_name('a').get_attribute('href')
    36.         baiurl=requests.get(zu,headers=headers,allow_redirects=False)
    37.         true_url=baiurl.headers['Location']
    38.         print(t)
    39.         print(true_url)
    40.         f.write(true_url+'\n')
    41. baidu_url()

    模拟登录

    1. from selenium import webdriver
    2. from selenium.webdriver.common.keys import Keys
    3. from time import sleep
    4. br=webdriver.Chrome()
    5. br.get('https://localhost:3443/#/login')
    6. input=br.find_element_by_id('txtEmailAddress').send_keys('2920015236@qq.com')
    7. input=br.find_element_by_id('txtPassword').send_keys('x5201314..')
    8. dj=br.find_element_by_id('btnLogin').click()