【代码】基于requests库对景点评论信息的爬取

原创

已于 2023-03-01 09:04:51 修改 · 176 阅读

5 ·

CC 4.0 BY-SA版权

文章标签：

#python #爬虫

于 2023-02-28 15:40:31 首次发布

修改data中的id即可爬取不同景点的信息

from gevent import monkey
monkey.patch_all()
import gevent
import requests
import openpyxl
import time

allList = []
#specId:37794,
def comment(specId,page):
    url = "https://m.tuniu.com/mapi/tour/getMenpiaoComment"
    params = {
        "specId":specId,
        "currentPage":page,
        "_":"1612702032902075249254887738041",
    }
    headers = {
        "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36",
        "referer":"https://m.tuniu.com/h5/tour/comment/37794/4",
    }

    res = requests.get(url,headers=headers,params=params)
    results = res.json()["data"]
    #共有页数
    pageNum = results["pageNums"]
    for result in results["remarkList"]:
        #评论者ID
        author = result["userName"]
        #评论时间
        date = result["remarkTime"]
        #总评分
        score = re