使用selenium爬取36氪

• 代码
• 代码分析
  （图片在最下面）

from selenium import webdriver

chrome_driver=r"C:\Users\yandi\AppData\Local\Programs\Python\Python37-32\chromedriver.exe"
driver=webdriver.Chrome(executable_path=chrome_driver)
driver.get('https://36kr.com/')
#获取资讯栏
driver.find_element_by_xpath('//*[@id="information"]').click()
#%%获取每一条资讯的信息
typelist,authorlist,titlelist = [],[],[]
i = 1
while(True):
    try:
        type = driver.find_element_by_xpath(
            '//div[@class="information-flow-list"]/div['+str(i)+']//span[@class="kr-flow-bar-motif"]/a').text
        typelist.append(type)

        author = driver.find_element_by_xpath(
            '//div[@class="information-flow-list"]/div['+str(i)+']//a[@class="kr-flow-bar-author"]').text
        authorlist.append(author)

        title = driver.find_element_by_xpath(
            '//div[@class="information-flow-list"]/div['+str