Python爬虫：1药城店铺爬虫（完整代码）

⭐️⭐️⭐️⭐️⭐️欢迎来到我的博客⭐️⭐️⭐️⭐️⭐️
🐴作者：秋无之地

🐴简介：CSDN爬虫、后端、大数据领域创作者。目前从事python爬虫、后端和大数据等相关工作，主要擅长领域有：爬虫、后端、大数据开发、数据分析等。

🐴欢迎小伙伴们点赞👍🏻、收藏⭐️、留言💬、关注🤝，关注必回关

一、确定目标数据

1、先打开目标网站，找到目标数据所在的页面，点击逛店铺

2、找到目标数据所在的api或页面

通过f12打开调试模式，通过搜索关键词，找到关键词所在的api或页面

3、观察请求参数

1）请求参数：有sign和token加密参数

2）翻页：position参数变动了，1_0_0表示第一页，2_0_0表示第二页。

二、请求接口

使用requests库请求接口，返回数据

def get_shop_list(self,per=10,position='1_0_0'):
    '''
    获取店铺列表
    :param per:每页展示条数
    :param position:开始位置
    :return:
    '''
    try:
        url = self.uri + "/druggmp/index/shopList"
        params = {
            "traderName":"yaoex_pc",
            "trader":"pc",
            "closesignature":"yes",
            "timestamp":int(time.time()*1000),
        }
        data = {
            "traderName":"yaoex_pc",
            "trader":"pc",
            "closesignature":"yes",
            "timestamp":int(time.time()*1000),
            "token":self.token,
            "queryAll":"yes",
            "isSearch":"yes",
            "per":per,
            "position":position,
        }
        self.log_.info(f"入参：{data}")
        resp = requests.post(url,headers=self.header,params=params,data=data).json()
        self.log_.info(f"出参数量：{len(resp['data']['shopList'])}")
        return resp['data']['shopList']
    except Exception as e:
        self.log_.error(str(e))
        return []

三、数据解析

将返回的数据进行正则匹配，然后通过遍历提取目标数据

'''获取店铺列表'''
shop_list = self.get_shop_list(per=10,position=position)
if not len(shop_list):
    self.log_.info('已经爬完，结束！')
    break
#遍历店铺
for shop_ in shop_list:
    #店铺id
    shop_id = shop_['enterpriseId']
    #店铺名称
    shop_name = shop_['shopName']
    #店铺logo
    logo = shop_['logo']
    #是否自营
    self_str = shop_['shopExtTypeText']
    if self_str and self_str=='自营':
        is_self = 1
    else:
        is_self = 0
    #城市
    if 'shipAddress' in shop_:
        city = shop_['shipAddress']
    else:
        city = ''

四、数据存储

数据解析后，对数据进行拼接，然后持久化，存在csv文件

sql = f'''replace into yyc_shop(shop_id,shop_name,logo,shelves,is_self,biz_code,biz_url,yao_url,qs_url,official_name,province,city) 
values('{shop_id}','{shop_name}','{logo}',{shelves},{is_self},'{biz_code}','{biz_url}','{yao_url}','{qs_url}','{official_name}','{province}','{city}')'''
self.log_.info(f"插入sql：{sql}")
self.base_.mysql_data(sql)

文件内容：

五、完整代码

完整代码如下：

def get_shop_list(self,per=10,position='1_0_0'):
    '''
    获取店铺列表
    :param per:每页展示条数
    :param position:开始位置
    :return:
    '''
    try:
        url = self.uri + "/druggmp/index/shopList"
        params = {
            "traderName":"yaoex_pc",
            "trader":"pc",
            "closesignature":"yes",
            "timestamp":int(time.time()*1000),
        }
        data = {
            "traderName":"yaoex_pc",
            "trader":"pc",
            "closesignature":"yes",
            "timestamp":int(time.time()*1000),
            "token":self.token,
            "queryAll":"yes",
            "isSearch":"yes",
            "per":per,
            "position":position,
        }
        self.log_.info(f"入参：{data}")
        resp = requests.post(url,headers=self.header,params=params,data=data).json()
        self.log_.info(f"出参数量：{len(resp['data']['shopList'])}")
        return resp['data']['shopList']
    except Exception as e:
        self.log_.error(str(e))
        return []

'''获取店铺列表'''
shop_list = self.get_shop_list(per=10,position=position)
if not len(shop_list):
self.log_.info('已经爬完，结束！')
break
#遍历店铺
for shop_ in shop_list:
#店铺id
shop_id = shop_['enterpriseId']
#店铺名称
shop_name = shop_['shopName']
#店铺logo
logo = shop_['logo']
#是否自营
self_str = shop_['shopExtTypeText']
if self_str and self_str=='自营':
    is_self = 1
else:
    is_self = 0
#城市
if 'shipAddress' in shop_:
    city = shop_['shipAddress']
else:
    city = ''

'''获取店铺上架数'''
shelves = self.get_shop_drug_count(shop_id=shop_id)

'''获取店铺证件'''
shop_info = self.get_shopcert(shop_id=shop_id)
#地址
address = shop_info['data']['baseInfo']['address']
#省份
try:
    if city and city in address:
        province = address.split(city)[0]
    else:
        provs = address.split('省')
        province = provs[0]
        city = provs[1].split('市')[0]
except:
    province = ''
#供应商全称
official_name = shop_info['data']['baseInfo']['enterpriseName']
#图片列表
img_files = shop_info['data']['files']
# 企业营业执照
biz_url = ''
# 经营许可证
yao_url = ''
# 质量体系调查表
qs_url = ''
if len(img_files):
    for i in img_files:
        if '营业执照' in i['typeName']:
            biz_url = i['filePath']
        if '经营许可证' in i['typeName']:
            yao_url = i['filePath']
        if '质量体系调查表' in i['typeName']:
            qs_url = i['filePath']

'''获取店铺营业执照编码'''
biz_code = ''
if biz_url:
    biz_code = self.get_shop_biz_code(img_link=biz_url)

#替换插入数据库
sql = f'''replace into yyc_shop(shop_id,shop_name,logo,shelves,is_self,biz_code,biz_url,yao_url,qs_url,official_name,province,city) 
values('{shop_id}','{shop_name}','{logo}',{shelves},{is_self},'{biz_code}','{biz_url}','{yao_url}','{qs_url}','{official_name}','{province}','{city}')'''
self.log_.info(f"插入sql：{sql}")
self.base_.mysql_data(sql)