【Python爬虫】IOS苹果商店指定APP评论爬取

import requests
import json
import time
import random
import pandas as pd 
from random import randint


app_id='1288515333'
### 设置部分
# app_id='1419975581'  # 设置app的id
reviews_count=450  # 设置采集的数量


### 采集部分
all_list=[]
for page_num in range(10000000):
    
    offset=page_num*10
    if offset>=reviews_count:
        break
    print('*'*60)
    print('已采集{}个'.format(offset+10))
    api='https://amp-api.apps.apple/v1/catalog/cn/apps/{}/reviews?l=zh-Hans-CN&offset={}&platform=web&additionalPlatforms=appletv%2Cipad%2Ciphone%2Cmac'.format(app_id,offset)
    headers={
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36',
        'authorization': 'Bearer eyJhbGciOiJFUzI1NiIsInR5cCI6IkpXVCIsImtpZCI6IlU4UlRZVjVaRFMifQ.eyJpc3MiOiI3TktaMlZQNDhaIiwiaWF0IjoxNjEzMTY5Mzg0LCJleHAiOjE2MTYxOTMzODR9.AyRdwIabKUIAOzUjwhw4tdWdfj4BSkUxpctFNg19A87VmOe1iplzpvcKlIJhb5mfOwi27UdVfDCRzSn6iT8PoA'
        # Bearer eyJhbGciOiJFUzI1NiIsInR5cCI6IkpXVCIsImtpZCI6IlU4UlRZVjVaRFMifQ.eyJpc3MiOiI3TktaMlZQNDhaIiwiaWF0IjoxNjEzMTY5Mzg0LCJleHAiOjE2MTYxOTMzODR9.AyRdwIabKUIAOzUjwhw4tdWdfj4BSkUxpctFNg19A87VmOe1iplzpvcKlIJhb5mfOwi27UdVfDCRzSn6iT8PoA
    }
    
    while True:
        try:
            while True:
                try:
                    response=requests.get(url=api,headers=headers)
                    break
                except requests.exceptions.ConnectTimeout:
                    time.sleep(randint(1,3))
                    continue
                except requests.exceptions.ReadTimeout:
                    time.sleep(randint(1,3))
                    continue
                except requests.exceptions.ConnectionError:
                    time.sleep(randint(1,3))
                    continue
                except requests.exceptions.ChunkedEncodingError:
                    time.sleep(randint(1,3))
                    continue
            json=response.json()
            info_list=json['data']
            break
        except KeyError:
            time.sleep(2)
            continue

    for info in info_list:
        # print(info)
        rating=info['attributes']['rating']
        title=info['attributes']['title']
        date=info['attributes']['date']
        review=info['attributes']['review']
        info=[rating,title,date,review]
        all_list.append(info)
    time.sleep(1)

columns=['评分','标题','日期','评论']
df=pd.DataFrame(data=all_list,columns=columns)
df.to_csv(r'C:\Users\kww\Desktop\移动端爬取\{}.csv'.format(app_id),index=False)

结果展示：