Python爬虫实战项目：医疗资源数据采集，分析统计，数据大屏

说明此处仅展示黑龙江省的数据 # --------------------------------------------------------------------------------------------- # # 爬取具体数据 # {'哈尔滨盛京白癜风医学研究院': 'https://yyk.99.com.cn/nangang/105610/jianjie.html', # '黑龙江省青年医学会附属医院': 'https://yyk.99.com.cn/haerbin/98419/jianjie.html',........} for k, v in info.items(): # # 访问子网，并保存数据 responce = requests.get(url=v, headers={"user-agent": ua.chrome}) if responce.status_code == 200: responce.encoding = "utf-8" html = responce.text with open("first.html", mode="w", encoding="utf-8") as f: f.write(html) name = k link = v try: chuang_sum = re.search(r'病床数量</span></td><td><span>(?P<c_n>\d+)</span>', html, re.S | re.M).group( "c_n") # 病床数量 except: chuang_sum = 0 # 病床数量 try: people_yi_h = re.search( r'<td><span>医护人数</span></td><td><a href="/[a-z]+/\d+/zhuanjia.html">(?D<Pnum>\d+)</a>', html, re.S | re.M).group("Dnum") # 医护人员数 except: people_yi_h = 0 # 医护人员数 try: people_jiuCi = re.search(r'<td><span>年门诊量</span></td><td><span>(?P<Pnum>\d+)</span></td>', html, re.S | re.M).group("Pnum") # 年就诊人次 except: people_jiuCi = 0 # 年就诊人次 privice = "黑龙江省" city_ = city[count].split("(")[0] # 城市 with open("黑龙江省医疗资源统计.csv", mode="a", encoding="utf-8", newline='') as f: wf = csv.writer(f) wf.writerow([name, link, chuang_sum, people_yi_h, people_jiuCi, privice, city_]) time.sleep(100) # 每次爬完一个医院数据，休息100秒 else: name = k link = v chuang_sum = 0 # 病床数量 people_yi_h = 0 # 医护人员数 people_jiuCi = 0 # 年就诊人次 privice = "黑龙江省" city_ = city[count].split("(")[0] # 城市 baocuo_W.append(dict(zip(k, v))) # 报错记录 with open("黑龙江省医疗资源统计.csv", mode="a", encoding="utf-8", newline='') as f: wf = csv.writer(f) wf.writerow([name, link, chuang_sum, people_yi_h, people_jiuCi, privice, city_]) time.sleep(random.randint(10, 100)) # 每次爬完一个医院数据，休息一定时间