评价"/>
对python的评价
旅游景点代码(地址要用手机版的携程搜自己想搜的景点):
import urllib.request
from bs4 import BeautifulSoup
import pymysql.cursors
import requests
import json
import datetime
def deal_json_invaild(data):
data = data.replace("\n", "").replace("\r", "").replace("\n\r", "").replace("\r\n", "").replace("\t", "").replace("\\\"","\"").replace("","")
data = data.replace('":"{"', "**testPasswors**5")\
.replace('":"', '&&testPassword&&')\
.replace('","', "$$testPassword$$")\
.replace('":{"', "**testPasswors**1")\
.replace('"},"', "**testPasswors**2")\
.replace(',"', "**testPasswors**3")\
.replace('{"', "@@testPassword@@")\
.replace('"}', "**testPassword**")\
.replace('":', "**testPasswors**4")\
data = data.replace('"', '”')\
.replace("**testPasswors**5","\":{\"").replace('&&testPassword&&', '":"').replace('$$testPassword$$', '","').replace('**testPasswors**1','":{"').replace('**testPasswors**2','"},"').replace('@@testPassword@@', '{"').replace('**testPassword**','"}').replace('**testPasswors**3',',"').replace('**testPasswors**4','":').replace('\\"','\"').replace(' ','').replace("resourceExtraInfo ","resourceExtraInfo").replace("\n", "").replace("\r", "").replace("\n\r", "").replace("\r\n", "").replace("\t", "").replace(r"\"","\"").replace("","").replace("}\"","}")
return data
headers={
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Trident/7.0; rv:11.0) like Gecko",
"Content-Type": "application/json"
}
f = open("data.txt","w",encoding='utf8')
for x in range(302,303):
# 综合评价
payload={
"CommentResultInfoEntity": {"BusinessId": "16588","BusinessType": 11,"ChannelType": 7,"CommentTagId": 0,"ImageFilter": 'false',"PageIndex": x,"PageSize": 10,"PoiId": 0,"SortType": 3,"StarType": 0,"TouristType": 0,"VideoImageHeight": 392,"VideoImageWidth": 700},"contentType": "json",
"head": {"auth": "","cid": "09031081211299101374","ctok": "","cver": "1.0","extension": [{"name": "protocal", "value": "https"}],"lang": "01","sid": "8888","syscode": "09"}
}
#好评
# payload={
# "CommentResultInfoEntity": {"BusinessId": "16588","BusinessType": 11,"ChannelType": 7,"CommentTagId": -11,"ImageFilter": 'false',"PageIndex": x,"PageSize": 10,"PoiId": 0,"SortType": 3,"StarType": 0,"TouristType": 0,"VideoImageHeight": 392,"VideoImageWidth": 700},"contentType": "json",
# "head": {"auth": "","cid": "09031081211299101374","ctok": "","cver": "1.0","extension": [{"name": "protocal", "value": "https"}],"lang": "01","sid": "8888","syscode": "09"}
# }
# #差评
# payload={
# "CommentResultInfoEntity": {"BusinessId": "16588","BusinessType": 11,"ChannelType": 7,"CommentTagId": -11,"ImageFilter": 'false',"PageIndex": x,"PageSize": 10,"PoiId": 0,"SortType": 3,"StarType": 0,"TouristType": 0,"VideoImageHeight": 392,"VideoImageWidth": 700},"contentType": "json",
# "head": {"auth": "","cid": "09031081211299101374","ctok": "","cver": "1.0","extension": [{"name": "protocal", "value": "https"}],"lang": "01","sid": "8888","syscode": "09"}
# }
r = requests.post('=09031081211299101374&__gw_appid=99999999&__gw_ver=1.0&__gw_from=10650019636&__gw_platform=H5', json=payload,headers=headers)
soup = BeautifulSoup(r.text,'html.parser')
soup = str(soup)
soup = deal_json_invaild(soup)
a = json.loads(soup)
# print(a)
for j in range(len(a["CommentResult"]["CommentInfo"])):
datetime1 = int(a["CommentResult"]["CommentInfo"][j]["PublishTime"][6:16]) #留言时间 这里是/Date()格式 里面是时间戳 js才能转换
dateArray = datetime.datetime.utcfromtimestamp(datetime1)
otherStyleTime = dateArray.strftime("%Y-%m-%d %H:%M:%S")
address,level='None','None'
print(not a["CommentResult"]["CommentInfo"][j]["UserInfoModel"])
if a["CommentResult"]["CommentInfo"][j]["UserInfoModel"]:
address = str(a["CommentResult"]["CommentInfo"][j]["UserInfoModel"]["UserDistrictName"]) #用户地址
level = str(a["CommentResult"]["CommentInfo"][j]["UserInfoModel"]["MedalName"]) #用户级别
dd = "总评分:" +str(a["CommentResult"]["CommentInfo"][j]["TotalStar"]) + "\t评论时间:"+ otherStyleTime +" \t用户地址:"+address+" \t用户会员级别:"+level+" \t 评论:"+ a["CommentResult"]["CommentInfo"][j]["Content"]
print("第{0}列 第{1}个 {2}".format(x,j,dd))
f.write(dd+'\n')
中间一大堆replace是携程json很多不规则的地方 需要替换 想data:"{}"这种结构
发现只能搜前3000条,后面就搜不到了,不知道什么情况
还有综合评价和好评差评是分开的
用网页模拟点击:
这个参数0是综合 -11是好评 -12差评
更多推荐
对python的评价
发布评论