python爬虫之爬取携程景点评价（5）

 一、景点部分评价爬取

【携程攻略】携程旅游攻略,自助游,自驾游,出游,自由行攻略指南 (ctrip.com)

import requests
from bs4 import BeautifulSoup

if __name__ == '__main__':
    url = 'https://m.ctrip.com/webapp/you/commentWeb/commentList?seo=0&businessId=22176&businessType=sight&hideStatusBar=1&DistrictName=%E9%BB%84%E9%BE%99%E6%BA%AA&isBack=yes&from=https%3A%2F%2Fm.ctrip.com%2Fwebapp%2Fyou%2Fgspoi%2Fsight%2F104%2F0.html%3FpoiId%3D81011%26seo%3D0%26isHideNavBar%3DYES%26scene%3DDISTRICT%26ctm_ref%3Dch5_hp_bs_lst&'#目标访问网站url
    header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36 Edg/123.0.0.0"}

    req = requests.get(url=url,headers = header)#获取该网页内容
    req.encoding = 'utf-8'#防止中文乱码，还可以改成gbk
    html = req.text
    bes = BeautifulSoup(html,"lxml")

    div_contents = bes.find_all('div', class_='content_wrap')#找到里面的所有div标签
    if div_contents:
        count = 1
        for div_content in div_contents:
            all_info = div_content.text
            print(f'{count}: {all_info}')
            count += 1
    else:
        print('未找到指定的<div class="content_wrap">标签')

二、景点所有评价爬取

        通过搜索，发现请求方法不在是get,而是post,且预览并得不到我们需要的评论，反而是响应界面才可以，则针对这种情况，我们需要重新更改代码。

更改代码如下 

import requests
import json
import pandas as pd
from tqdm import tqdm

userNames = []
commentDetails = []
commentTimes = []

total_pages = 1

for pagen in tqdm(range(0, total_pages), desc='爬取进度', unit='页'):
    #payload参数实质上就是网络下的负载
    payload = {
        "arg": {
            "channelType": 7,
            "collapseTpte": 1,
            "commentTagId": 0,
            "pageIndex": pagen,
            "pageSize": 10,
            "resourceId":22176,
            "resourceType":11,
            "sourseType": 1,
            "sortType": 3,
            "starType": 0
        },
        "head": {
            "cid": "09031081213865125571",
            "ctok": "",
            "cver": "1.0",
            "lang": "01",
            "sid": "8888",
            "syscode": "09",
            "auth": "",
            "xsid": "",
            "extension": []
        }
    }

    #网络的标头中的url路径，采用POST请求方法，其？后面的内容就是payload
    postUrl = "https://m.ctrip.com/restapi/soa2/13444/json/getCommentCollapseList"

    html = requests.post(postUrl, data=json.dumps(payload)).text
    html_1 = json.loads(html)#html_1实质就是网络下面的响应界面

    # 检查响应中是否存在'items'
    if 'items' in html_1["result"]:
        commentItems = html_1["result"]["items"]
        for i in range(0, len(commentItems)):
            # 在访问元素之前检查当前项是否不为None
            if commentItems[i] is not None and 'userInfo' in commentItems[i] and 'userNick' in commentItems[i][
                'userInfo']:
                userName = commentItems[i]['userInfo']['userNick']
                commentDetail = commentItems[i]['content']
                commentTime = commentItems[i]['publishTypeTag']

                userNames.append(userName)
                commentDetails.append(commentDetail)
                commentTimes.append(commentTime)

# 创建 DataFrame
df = pd.DataFrame({
    '用户评论内容': commentDetails,
    '用户名': userNames,
    '用户评论时间': commentTimes
})

# 保存到 Excel 文件
df.to_excel('只爬黄龙溪评论1223url.xlsx', index=False, encoding='utf-8')

三、不同景点所有评价爬取

 可以看出，不同景点的resourceId不一样，即更改diamagnetic中的resourceId的数字即可

四、URL编码很乱如何解码

UrlEncode编码/UrlDecode解码 - 站长工具 (chinaz.com)

五、No module named 'pandas'问题解决

ModuleNotFoundError: No module named 'pandas'

常用源：

清华：https://pypi.tuna.tsinghua.edu.cn/simple
阿里云：http://mirrors.aliyun.com/pypi/simple/
中国科技大学 https://pypi.mirrors.ustc.edu.cn/simple/