最近好像上映了不少电影,而且我好久没看过豆瓣了,这里给大家分享一个爬取豆瓣评论的selenium脚本。
首先我们打开电影的短片区:
这里大家注意,虽然全部写着有10万多条,其实豆瓣电影里只显示前600条。。。。。
1、先将selenium的相关包导进来
import time
import tqdm
import random
import requests
import json
import pandas as pd
import os
from selenium import webdriver
from selenium.webdriver.common.by import By
2、用edge浏览器打开相关电影评论网页
browser = webdriver.Edge()
time.sleep(5)
browser.get('https://movie.douban.com/subject/26925611/comments?percent_type=h&limit=20&status=P&sort=new_score')
3、用xpath语句定位想要爬取的数据,这里就爬了评论数据来做lda等后续的数据分析
from selenium.common.exceptions import NoSuchElementException, StaleElementReferenceException, ElementClickInterceptedException
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
max_clicks = 100
click_count = 0
comments=[]
ratings=[]
urls=[]
try:
while click_count < max_clicks:
try:
li_list = browser.find_elements_by_xpath('//div[@id="comments"]/div')
for li in li_list:
try:
comment = li.find_element_by_xpath('.//span[@class="short"]').text
print("comment:>>",comment)
comments.append(comment)
except:
pass
next_link = WebDriverWait(browser, 10).until(EC.element_to_be_clickable((By.CLASS_NAME, "next")))
next_link.click()
click_count += 1 # 增加点击次数计数器
time.sleep(2) # 等待页面加载
except Exception as e:
print("无法找到或点击按钮:", e)
break
except (StaleElementReferenceException, ElementClickInterceptedException):
pass # 元素不可用或者无法点击,继续下一次循环处理下一页内容
df = pd.DataFrame({'comment':comments,'rating':0})
df.to_csv("./comments.csv", index=False)
4、结果如下: