【求助】selenium+chromedriver爬取微博问题

逆夏桑 2019-01-28 02:01:15



from selenium import webdriver

import time

import csv



def login():

    driver.get("https://passport.weibo.cn/signin/login?entry=mweibo&res=wel&wm=3349&r=https%3A%2F%2Fm.weibo.cn%2Fdetail%2F4332476089824509")

    driver.implicitly_wait(5)

    user_name = driver.find_element_by_id("loginName")

    user_name.send_keys("xxxxxx")

    user_psd = driver.find_element_by_id("loginPassword")

    user_psd.send_keys("xxxxxx")

    submit = driver.find_element_by_id("loginAction")

    submit.click()

    print("准备登录。。")

    time.sleep(9)



def data_write(info_list):

    with open("weibo_content.csv","a",encoding="gbk") as f:

        csvfile = csv.writer(f)

        csvfile.writerow(info_list)



def spider():

    driver.get("https://m.weibo.cn/")

    time.sleep(6)

    all_messages = driver.find_elements_by_xpath("//div[@class='pannelwrap']/div[@class='wb-item-wrap']")

    #找到微博内容框框

    for each_frame in all_messages:

        time.sleep(2)

        pub_id = each_frame.find_element_by_xpath("header[@class='weibo-top m-box']/div[2]/div[1]/a/h3")[0].text.strip()

        pub_url = "https://m.weibo.cn/" + each_frame.find_element_by_xpath("header[@class='weibo-top m-box']/div[2]/div[1]/a")[0].get_attribute("href")

        pub_weibo = each_frame.find_element_by_xpath("article[@class='weibo-main']/div[1]/div[1]/div[1]")[0].text.strip()

        info_list = [pub_id,pub_url,pub_weibo]

        data_write(info_list)

        print("正在写入：",pub_id)



if __name__ == "__main__":

    #初始化selenium

    driver = webdriver.Chrome()



    login()



    while True:

        spider()

        time.sleep(300)

报错的语句是：pub_id = each_frame.find_element_by_xpath("header[@class='weibo-top m-box']/div[2]/div[1]/a/h3")[0].text.strip()
报错的内容是can not locate pub_id,或者是AttributeError: 'list' object has no attribute 'find_element_by_xpath'
咋解决啊？感谢大大们

...全文