python3 获取商店里App评论+解析+存档+筛选

业余爱好

抓个接口练练

开发环境

mac OS 10.15.6

python 3.8.3

包括创建类、函数、请求接口、数据解析、数据类型转换、函数调用、实现等

保存的text在python执行文件的同级目录下，并未做自定义的文件路径，毕竟要的是结果 嘿嘿

#!/usr/bin/python
#coding=utf8
#-*- encoding: UTF-8 -*-
import requests
import json

class AFNet(object):

	# 接口中获取feed
	def arrFromDic(self,dic):
		user_dic = json.loads(dic)
		feed = user_dic['feed'] 
		entry = []
		if feed.get('entry'):
			entry = feed['entry']
		return  entry 

	#获取详细信息
	def getInfo(self,page,ids):
		# 去掉可能包含id
		ids = ids.replace("id", "")
		url = "https://itunes.apple.com/cn/rss/customerreviews/page=%s/id=%s/sortby=mostrecent/json"%(page, ids)
		response = self.get(url);

		# print(response)
		return response

	# get请求
	def get(self,url):
		print( "请求地址 = "+ url)
		response = requests.get(url=url)
		return response
	
	# post请求
	def post(self,url,parmars):
		print(url)
		print(parmars)
		requests.post(url=url,data={'key1':'value1','key2':'value2'},headers={'Content-Type':'application/x-www-form-urlencoded'})
		response = requests.get(url=url)
		return response.text

	# 获取所有数据
	def getAllDate(self,ids):
		entry = []
		#便历接口	
		for page in range(1,20):
			st = self.getInfo(page,ids)
			# st = self.getInfoNew(page,ids)
			text = st.text
			# print(st)
			code = st.status_code
			count = len(text)
			if code == 200:
				entry2 = []
				re = self.arrFromDic(text)
				if isinstance(re,dict):
					entry2.append(re)
				else:
					entry2 = re
				count = len(entry2)
				if count <= 0:
					print("没有更多数据请求结束")
					break
				else:
					entry = entry + entry2
					text = "第 %s 页 %s 条数据"%(page,count)
					print (text)
			else:
				print("请求接口返回异常结束 " + str(code))
				break
		return  entry

	# 元数据解析 
	def managerArr(self,entry):
		print ('共 ' + str(len(entry)) + " 条数据")
		arrResult= []
		for dic in entry:
			author =  dic["author"]

			name =  author["name"]
			namelabel =  name["label"]

			content =  dic["content"]
			contentlabel =  content["label"]

			title =  dic["title"]
			titlelabel =  title["label"]

			version =  dic["im:version"]
			versionlabel =  version["label"]

			rating =  dic["im:rating"]
			ratinglabel =  rating["label"]

			voteSum =  dic["im:voteSum"]
			voteSumlabel =  voteSum["label"]


			start = ""
			for x in range(0,int(ratinglabel)):
	 			start =  start +  "⭐️"

			# print (resultSrr)
			# arrResult.append(resultSrr)

			dicNew = {
			"versionlabel":versionlabel,
			"start":start,
			"ratinglabel":ratinglabel,
			"namelabel":namelabel,
			"titlelabel":titlelabel,
			"contentlabel":contentlabel,
			"voteSumlabel":voteSumlabel,
			"ratinglabel":ratinglabel
			}

			arrResult.append(dicNew)

			
		return  arrResult

	# 字典转字符串  星数 
	#  entry   数组中的字典数据
	#  strarCount  判断星数
	#  type  判断条件 1== 2<= 3>=
	def managerDicToString(self,entry,strarCount,type):
		arrResult= []
		for dic in entry:
			start        = dic["start"]
			namelabel    = dic["namelabel"]
			contentlabel = dic["contentlabel"]
			titlelabel   = dic["titlelabel"]
			versionlabel = dic["versionlabel"]
			ratinglabel  = dic["ratinglabel"]
			voteSumlabel = dic["voteSumlabel"]
			start        = dic["start"]

			resultSrr = ""
			resultSrr = resultSrr + "…………………………………………………………………………………………\n"
			resultSrr = resultSrr + "版本 = %s\n" %(versionlabel)
			resultSrr = resultSrr + "星数 = %s\n" %(start)
			resultSrr = resultSrr + "评级 = %s\n" %(ratinglabel)
			resultSrr = resultSrr + "昵称 = %s\n" %(namelabel)
			resultSrr = resultSrr + "标题 = %s\n" %(titlelabel)
			resultSrr = resultSrr + "内容 = %s\n" %(contentlabel)
			resultSrr = resultSrr + "投票 = %s\n" %(voteSumlabel)


			if type == 1:
				if int(strarCount) == int(ratinglabel) :
					print("resultSrr = ",resultSrr)
					arrResult.append(resultSrr)
					pass
				pass

			if type == 2:
				if int(ratinglabel) <= int(strarCount)  :
					print("resultSrr = ",resultSrr)
					arrResult.append(resultSrr)
					pass
				pass

			if type == 3:
				if int(ratinglabel) <= int(strarCount) :
					print("resultSrr = ",resultSrr)
					arrResult.append(resultSrr)
					pass
				pass
		return  arrResult

	# 保存文件
	def SaveFile(self,arr,name):
		# print arrResult
		count = len(arr)
		text = "总数=%s"%(count)
		# 文件全名
		allName = name + "." + "txt"
		try:
			f = open(allName,mode='w') 
			#字典转字符串
			str1 = ''.join(saveStrArrNew) #数组转字符串
			f.write(str1)  # write 写入
			f.close()   #关闭文件
			print("保存成功")
			return True
		except smtplib.SMTPException:
			print("保存失败")
			return False


if __name__ == '__main__':

	# 请求类的初始化
	afn = AFNet()
	print("开始")
	# app的id 带不带id 都可以 接口有判断逻辑 方便无脑操作 哈哈
	ids = '930368978'
	ids = 'id930368978'

# str1 = json.dumps(arr)  

	# 请求分页数据
	entry = afn.getAllDate(ids)

	saveStrArr = afn.managerArr(entry)
	# 字典转字符串  星数 
	#  entry   数组中的字典数据
	#  strarCount  判断星数
	#  type  判断条件 1== 2<= 3>=
	saveStrArrNew = afn.managerDicToString(saveStrArr,3,2)
	# 保存文件
	afn.SaveFile(saveStrArrNew,"反馈")

2020-08-25 七夕红豆 中国东方情人节

更新获取评论数量为空的崩溃问题

增加参数id的是否带有id前缀的判断

2020-08-26

更新数据解析

2020-08-27

封装优化

2020-12-15

增加筛选规则