ip代理池 + sleep 爬取美团数据

https://github.com/Python3WebSpider/ProxyPool
安装相应文件 & python run.py (3.7以上)

安装redis 并提前运行

 

#! -*- encoding:utf-8 -*-
import requests
import json,csv,time
from urllib import request
import datetime,zlib,base64

def str_replace(string):
    return string.replace('/', '%2F') \
        .replace('+', '%2B') \
        .replace('=', '%3D') \
        .replace(':', '%3A')

simulateBrowserHeader = {
    'Accept': '*/*',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Host': 'sh.meituan.com',
    'Referer': 'https://sh.meituan.com/meishi/',
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36"
}

PROXY_POOL_URL = 'http://localhost:5555/random'
def get_proxy():
    try:
        response = requests.get(PROXY_POOL_URL)
        if response.status_code == 200:
            return response.text
    except ConnectionError:
        return None

# 生成token
def encode_token():
    ts = int(datetime.datetime.now().timestamp() * 1000)
    token_dict = {
        'rId': 100900,
        'ver': '1.0.6',
        'ts': ts,
        'cts': ts + 100 * 1000,
        'brVD': [1190,1030],
        'brR': [[1011,875],[1011,875],24,24],
        'bI': ['https://sh.meituan.com/meishi/b4739/', ''],
        'mT': [],
        'kT': [],
        'aT': [],
        'tT': [],
        'aM': '',
        'sign': "eJwdzU1OxCAYBuC7zILlQIFOWxMWSCExMe48ALY4JZafwIeJV/A+Rg9kPIfN7J7F+3OyxdmHVTC0WHAHCFo8fDzZ4MTvz+ff1zdafYyuqNQiSIByZFDK4EOrKq1OdASl4q8+PpddbAC53mFct3NwHpqN5yUFfLhuHr8wnGNHMMr2eitmW+DYFh29oLxbeE0liA4VX98e3bvbD9dUQKBW3e24Nb+KyUhyIcNoKOkpM4qo+36eqdRSDnRSnFMz0lHrTk6zNoPqB85nMzBm9Cg5Jad/Pg9QMw=="
    }
    encode = str(token_dict).encode()
    compress = zlib.compress(encode)
    b_encode = base64.b64encode(compress)
    token = str(b_encode, encoding='utf-8')
    return token

if __name__ == '__main__':

    originUrl = str_replace('https://sh.meituan.com/meishi/b4739/')
    token_encode = encode_token()
    token = str_replace(token_encode)

    for num in range(1,70):
        print(num)
        time.sleep(2.5)
        url = 'https://sh.meituan.com/meishi/api/poi/getPoiList?' \
                  'cityName=上海' \
                  '&cateId=0' \
                  '&areaId=4739' \
                  '&sort=' \
                  '&dinnerCountAttrId=' \
                  '&page=%d' \
                  '&userId=' \
                  '&uuid=9FA06078F20523FC0CB5DD2AEAA729C442F828EE1A9DEF7C5744DF733FE8A420' \
                  '&platform=1' \
                  '&partner=126' \
                  '&originUrl=%s' \
                  '&riskLevel=1' \
                  '&optimusCode=1' \
                  '&_token=%s' % (num, originUrl, token)
        
        proxy = get_proxy()
        while proxy == None:
            proxy = get_proxy()
        jsons = None
        response = requests.get(url, headers=simulateBrowserHeader, proxies={"http":"http://HKGYJ5BCT545T08D:[email protected]:9020"})
        # print(response.text)
        # try:
        #     response = requests.get(url, headers=simulateBrowserHeader, proxies={"http": proxy })
        #     jsons = json.loads(response.text)
        # except:
        #     print("error")
        #     proxy = get_proxy()
        #     while proxy == None:
        #         proxy = get_proxy()
        #     response = requests.get(url, headers=simulateBrowserHeader, proxies={"http": proxy })
        #     jsons = json.loads(response.text)
        jsons = json.loads(response.text)

        data = jsons["data"]["poiInfos"]
        awrite = open('meishi_15.csv','a', newline='',encoding='utf-8')
        for i in data:
            title = i["title"]
            avgScore = i["avgScore"]
            address = i["address"]
            allCommentNum = i["allCommentNum"]
            csv_write = csv.writer(awrite, dialect='excel')
            csv_write.writerow([title, avgScore, address, allCommentNum])

print("END...")