Python:晚上把附近的足浴店都给爬了一遍,好兄弟针不戳!

import csv

import time

f = open(‘按摩data.csv’, mode=‘a’, encoding=‘utf-8’, newline=‘’)

csv_writer = csv.DictWriter(f, fieldnames=[

‘店铺名称’,

‘人均消费’,

‘店铺评分’,

‘评论人数’,

‘所在商圈’,

‘店铺类型’,

‘店铺地址’,

‘联系方式’,

‘营业时间’,

‘详情页’,

])

csv_writer.writeheader()

def get_shop_info(html_url):

headers = {

‘Cookie’: ‘_lxsdk_cuid=1742973e754c8-0755662a43e0a2-3962420d-1fa400-1742973e754c8; iuuid=1F1D4BFAA0B9CA777B0EC2B899C43AD6C5C9CDB370B86A51322AB71211B94277; cityname=%E9%95%BF%E6%B2%99; _lxsdk=1F1D4BFAA0B9CA777B0EC2B899C43AD6C5C9CDB370B86A51322AB71211B94277; _hc.v=f4f02748-8eb7-1ea7-385c-5899047aa1c1.1618907157; __mta=251035321.1598423295952.1598423295952.1621410161604.2; uuid=05f4abe326934bf19027.1634911815.1.0.0; rvct=1%2C70%2C30; _lx_utm=utm_source%3DBaidu%26utm_medium%3Dorganic; mtcdn=K; lt=knaBbvVTfN50cupoV5b87GJMXzkAAAAAAw8AAELrweWvhGhrM0fw6oTkLe5c6DGXJ6PCtxfyHgUPl3k-SVVR-Vs0LjzrGfewJhX8-g; u=266252179; n=qSP946594369; token2=knaBbvVTfN50cupoV5b87GJMXzkAAAAAAw8AAELrweWvhGhrM0fw6oTkLe5c6DGXJ6PCtxfyHgUPl3k-SVVR-Vs0LjzrGfewJhX8-g; unc=qSP946594369; firstTime=1634974011563; ci=70; _lxsdk_s=17cac0b849b-b3e-dac-85e%7C%7C10’,

‘Host’: ‘www.meituan.com’,

‘Referer’: ‘https://bj.meituan.com/’,

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36’,

}

response = requests.get(url=html_url, headers=headers)

print(response.text)

phone = re.findall(‘“phone”:“(.*?)”’, response.text)[0]

openTime = re.findall(‘“openTime”:“(.*?)”’, response.text)[0].replace(‘\n’, ‘’)

address = re.findall(‘“address”:“(.*?)”’, response.text)[0]

shop_info = [address, phone, openTime]

print(shop_info)

return shop_info

def get_shop_info(html_url):

headers_1 = {

‘Cookie’: ‘_lxsdk_cuid=1742973e754c8-0755662a43e0a2-3962420d-1fa400-1742973e754c8; iuuid=1F1D4BFAA0B9CA777B0EC2B899C43AD6C5C9CDB370B86A51322AB71211B94277; cityname=%E9%95%BF%E6%B2%99; _lxsdk=1F1D4BFAA0B9CA777B0EC2B899C43AD6C5C9CDB370B86A51322AB71211B94277; _hc.v=f4f02748-8eb7-1ea7-385c-5899047aa1c1.1618907157; uuid=96d0bfc90dfc441b81fb.1630669508.1.0.0; ci=30; rvct=30; mtcdn=K; lt=1vyIlUgnzqEfhjpxic8Whf_WGfwAAAAAbg4AAOEUVbolB83IgwxL1wwOGfvIpVZsnHpwF6bGZZ5yT_SL4V8GRr4_WKkQ4s2AcF6Tmg; u=266252179; n=qSP946594369; token2=1vyIlUgnzqEfhjpxic8Whf_WGfwAAAAAbg4AAOEUVbolB83IgwxL1wwOGfvIpVZsnHpwF6bGZZ5yT_SL4V8GRr4_WKkQ4s2AcF6Tmg; firstTime=1630669549381; unc=qSP946594369; _lxsdk_s=17bab7a163a-27-d8f-8fd%7C%7C113’,

# ‘Referer’: ‘https://sz.meituan.com/’,

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36’

}

response_1 = requests.get(url=html_url, headers=headers_1)

html_data = re.findall(‘“address”:“(.*?)”,“phone”:“(\d+)”’, response_1.text)[0]

return html_data

get_shop_info(‘https://www.meituan.com/meishi/193587069/’)

for page in range(0, 1537, 32):

time.sleep(2)

url = ‘https://apimobile.meituan.com/group/v4/poi/pcsearch/30’

data = {

‘uuid’: ‘05f4abe326934bf19027.1634911815.1.0.0’,

‘userid’: ‘266252179’,

‘limit’: ‘32’,

‘offset’: page,

‘cateId’: ‘-1’,

‘q’: ‘按摩’,

‘token’: ‘knaBbvVTfN50cupoV5b87GJMXzkAAAAAAw8AAELrweWvhGhrM0fw6oTkLe5c6DGXJ6PCtxfyHgUPl3k-SVVR-Vs0LjzrGfewJhX8-g’

}

headers = {

‘Referer’: ‘https://sz.meituan.com/’,

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36’

}

response = requests.get(url=url, params=data, headers=headers)

result = response.json()[‘data’][‘searchResult’]

for index in result:

shop_id = index[‘id’]

index_url = f’https://www.meituan.com/meishi/{shop_id}/’

shop_info = get_shop_info(index_url)

dit = {

‘店铺名称’: index[‘title’],

‘人均消费’: index[‘avgprice’],

‘店铺评分’: index[‘avgscore’],

‘评论人数’: index[‘comments’],

‘所在商圈’: index[‘areaname’],

‘店铺类型’: index[‘backCateName’],

‘店铺地址’: shop_info[0],

‘联系方式’: shop_info[1],

‘营业时间’: shop_info[2],

‘详情页’: index_url,

}

csv_writer.writerow(dit)

print(dit)

自我介绍一下,小编13年上海交大毕业,曾经在小公司待过,也去过华为、OPPO等大厂,18年进入阿里一直到现在。

深知大多数Python工程师,想要提升技能,往往是自己摸索成长或者是报班学习,但对于培训机构动则几千的学费,着实压力不小。自己不成体系的自学效果低效又漫长,而且极易碰到天花板技术停滞不前!

因此收集整理了一份《2024年Python开发全套学习资料》,初衷也很简单,就是希望能够帮助到想自学提升又不知道该从何学起的朋友,同时减轻大家的负担。

img

img

img

img

img

img

既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上前端开发知识点,真正体系化!

由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新

如果你觉得这些内容对你有帮助,可以扫码获取!!!(备注Python)

)

既有适合小白学习的零基础资料,也有适合3年以上经验的小伙伴深入学习提升的进阶课程,基本涵盖了95%以上前端开发知识点,真正体系化!

由于文件比较大,这里只是将部分目录大纲截图出来,每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频,并且后续会持续更新

如果你觉得这些内容对你有帮助,可以扫码获取!!!(备注Python)

img
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值