[开发测试]selenium爬取微博评论，点赞数，点赞时间

import time,re
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import time
import pandas as pd
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By


driver = webdriver.Chrome()
driver.get("https://login.sina.com.cn/signup/signin.php?")
# 60秒内输入完用户名和密码
time.sleep(50)
content_list = []
url_list = []

# 获取所有的url地址
for page in range(1,50):
    driver.get("https://s.weibo.com/weibo/%25E6%2596%25B9%25E6%25B4%258B%25E6%25B4%258B%25E5%25AE%25B6%25E6%259A%25B4?q=%E6%96%B9%E6%B4%8B%E6%B4%8B%E5%AE%B6%E6%9A%B4&typeall=1&suball=1&timescope=custom:2020-11-18-1:2020-12-18-23&Refer=g&page={}".format(page))
    time.sleep(6)
    for i3 in range(20):
        i3 += 1
        # 这个是点击单个评论
        try:
            ret2 = driver.find_element_by_xpath("//*[@id='pl_feedlist_index']/div[2]/div[{}]/div/div[1]/div[2]/div[2]/div[2]/div/div/ul/li[2]/a".format(i3))
            if len(ret2.text) > 2:
                print(ret2.text)
                url1 = driver.find_element_by_xpath("//*[@id='pl_feedlist_index']/div[2]/div[{}]/div/div[1]/div[2]/div[2]/div[2]/div/div/ul/li[2]/a".format(i3)).get_attribute("href")
                url2 = url1 + "&type=comment"
                print(url2)
                url_list.append(url2)
        except Exception as e:
            pass

'''循环操作，获取剩余页数的数据'''
for i2 in  url_list:
    driver.get(i2)
    time.sleep(5)
    i = 1
    while i:
        try:
            element = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CLASS_NAME, 'more_txt')))
            time.sleep(3)
            driver.find_element_by_xpath("//*[@class='list_ul']//a/span[@class='more_txt']").click()
            time.sleep(3)
        except Exception as e:
            break

    # 开始解析数据
    print("开始解析数据")
    time.sleep(4)
    li_list = driver.find_elements_by_xpath("//*[@class='list_ul']/div/div[2]")
    for li in li_list:
        print(li.text)
        try:
            item = {}
            anchor = re.split(r"\n", li.text)[0]
            item["anchor"] = re.split(r"：", anchor)[1]
            time.sleep(1)
            watch_num = re.split(r"\n", li.text)[2]
            item["watch_num"] = (re.match("?\d*", watch_num).group())[1:]
            time.sleep(1)
            item["time"] = re.split(r"\n", li.text)[3]
            print(item)
            content_list.append(item)
        except Exception as e:
            print(e)
        finally:
            pass

Comment = [z["anchor"] for z in content_list]
Likes = [zz["watch_num"] for zz in content_list]
time = [zzz["time"] for zzz in content_list]
data = pd.DataFrame({'Comment': Comment, 'Likes': Likes,'time':time})
data.to_excel("方洋洋家暴.xlsx")

driver.quit()




![爬取微博评论和点赞数还有点赞时间](https://img-blog.csdnimg.cn/1a355f7ce97447959f5ed04240bf0809.png?x-oss-process=image/watermark,type_ZHJvaWRzYW5zZmFsbGJhY2s,shadow_50,text_Q1NETiBAWW91QXJlTXlRdWVyeQ==,size_20,color_FFFFFF,t_70,g_se,x_16)