Python爬取百度旅游网站的景点

最新推荐文章于 2024-07-12 22:58:11 发布

NeumannDong

最新推荐文章于 2024-07-12 22:58:11 发布

阅读量1.3k

点赞数

分类专栏： Python爬虫

本文链接：https://blog.csdn.net/sinat_26290785/article/details/69941700

版权

Python爬虫专栏收录该内容

1 篇文章 0 订阅

订阅专栏

from selenium import webdriver
import csv
import time


link='https://lvyou.baidu.com/yuanmingyuan?&request_id=3137216805&lowflow=1&innerfr_pg=sceneListPg&accur_thirdpar=destination&idx=6'
# driver = webdriver.Chrome()
# driver = webdriver.Firefox(executable_path=r"D:\FireFox\firefox.exe")
driver = webdriver.Firefox()
driver.get(link)

header = ['id','pinglun']
with open('pinglun.csv','wb') as datacsv:
    csvwriter = csv.writer(datacsv,dialect=("excel"))
    csvwriter.writerow(header)

xiayiye = driver.find_element_by_class_name("tangram-pager-next").text
while xiayiye:
    for i in range(1,7):
        pinglun = driver.find_element_by_xpath('//*[@id="remark-container"]/div[3]/div['+str(i)+']/div[2]/div[2]/div[1]').text
        data = [i,pinglun.encode('utf-8')]
        with open("pinglun.csv", "a") as datacsv:
            csvwriter = csv.writer(datacsv, dialect=("excel"))
            csvwriter.writerow(data)
        print(i)
    print('click')
    driver.find_element_by_class_name("tangram-pager-next").click()
    time.sleep(2)