1 from bs4 importBeautifulSoup as bs2 from requests.exceptions importRequestException3 importrequests4 importre5 from DBUtils importDBUtils6
7 def main(response): #web页面数据提取与入库操作
8 html = bs(response.text, 'lxml')9 for data in html.find_all(name='div',attrs={"class":"content__list--item--main"}):10 try:11 print(data)12 Community_name = data.find(name="a", target="_blank").get_text(strip=True)13 name=str(Community_name).split(" ")[0]14 sizes=str(Community_name).split(" ")[1]15 forward=str(Community_name).split(" ")[2]16 flood = data.find(name="span",class_="hide").get_text(strip=True)17 flood=str(flood).replace(" ","").replace("/","")18 sqrt= re.compile("\d\d+㎡")19 area=str(data.find(text=sqrt)).replace(" ","")20 maintance=data.find(name="span",class_="content__list--item--time oneline").get_text(strip=True)21 maintance=str(maintance)22 price=data.find(name="span",class_="content__list--item-price").get_text(strip=True)23 price=str(price)24 print(name,sizes,forward,flood,maintance,price)25 insertsql = "INSERT INTO test_log.`information`(Community_name,size,forward,area,flood,maintance,price) VALUES"('"+name+"','"+sizes+"','"+forward+"','"+area+"','"+flood+"','"+maintance+"','"+price+"');"26 insert_sql(insertsql)27 except:28 print("have an error!!!")29
30 def insert_sql(sql): #数据入库操作
31 dbconn=DBUtils("test6")32 dbconn.dbExcute(sql)33
34 def get_one_page(urls): #获取web页面数据
35 try:36 headers = {"Host": "bj.lianjia.com",37 "Connection": "keep-alive",38 "Cache-Control": "max-age=0",39 "Upgrade-Insecure-Requests": "1",40 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",41 "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",42 "Sec-Fetch-Site": "none",43 "Sec-Fetch-Mode": "navigate",44 "Sec-Fetch-User": "?1",45 "Sec-Fetch-Dest": "document",46 "Accept-Encoding": "gzip, deflate, br",47 "Accept-Language": "zh-CN,zh;q=0.9",48 "Cookie": "lianjia_uuid=fa1c2e0b-792f-4a41-b48e-78531bf89136; _smt_uid=5cfdde9d.cbae95b; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2216b3fad98fc1d1-088a8824f73cc4-e353165-2710825-16b3fad98fd354%22%2C%22%24device_id%22%3A%2216b3fad98fc1d1-088a8824f73cc4-e353165-2710825-16b3fad98fd354%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E8%87%AA%E7%84%B6%E6%90%9C%E7%B4%A2%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22https%3A%2F%2Fwww.baidu.com%2Flink%22%2C%22%24latest_referrer_host%22%3A%22www.baidu.com%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC%22%7D%7D; _ga=GA1.2.1891741852.1560141471; UM_distinctid=17167f490cb566-06c7739db4a69e-4313f6b-100200-17167f490cca1e; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1588171341; lianjia_token=2.003c978d834648dbbc2d3aa4b226145cd7; select_city=110000; lianjia_ssid=fc20dfa1-6afb-4407-9552-2c4e7aeb73ce; CNZZDATA1253477573=1893541433-1588166864-https%253A%252F%252Fwww.baidu.com%252F%7C1591157903; CNZZDATA1254525948=1166058117-1588166331-https%253A%252F%252Fwww.baidu.com%252F%7C1591154084; CNZZDATA1255633284=1721522838-1588166351-https%253A%252F%252Fwww.baidu.com%252F%7C1591158264; CNZZDATA1255604082=135728258-1588168974-https%253A%252F%252Fwww.baidu.com%252F%7C1591153053; _jzqa=1.2934504416856578000.1560141469.1588171337.1591158227.3; _jzqc=1; _jzqckmp=1; _jzqy=1.1588171337.1591158227.1.jzqsr=baidu.-; _qzjc=1; _gid=GA1.2.1223269239.1591158230; _qzja=1.1313673973.1560141469311.1588171337488.1591158227148.1591158227148.1591158233268.0.0.0.7.3; _qzjto=2.1.0; srcid=eyJ0Ijoie1wiZGF0YVwiOlwiMThmMWQwZTY0MGNiNTliNTI5OTNlNGYxZWY0ZjRmMmM3ODVhMTU3ODNhNjMwODhlZjlhMGM2MTJlMDFiY2JiN2I4OTBkODA0M2Q0YTM0YzIyMWE0YzIwOTBkODczNTQwNzM0NTc1NjBlM2EyYTc3NmYwOWQ3OWQ4OWJjM2UwYzAwY2RjMTk3MTMwNzYwZDRkZTc2ODY0OTY0NTA5YmIxOWIzZWQyMWUzZDE3ZjhmOGJmMGNmOGYyMTMxZTI1MzIxMGI4NzhjNjYwOGUyNjc3ZTgxZjA2YzUzYzE4ZjJmODhmMTA1ZGVhOTMyZTRlOTcxNmNiNzllMWViMThmNjNkZTJiMTcyN2E0YzlkODMwZWIzNmVhZTQ4ZWExY2QwNjZmZWEzNjcxMjBmYWRmYjgxMDY1ZDlkYTFhMDZiOGIwMjI2NTg1ZGU4NTQyODBjODFmYTUyYzI0NDg5MjRlNWI0N1wiLFwia2V5X2lkXCI6XCIxXCIsXCJzaWduXCI6XCI2Yzk3M2U5M1wifSIsInIiOiJodHRwczovL2JqLmxpYW5qaWEuY29tL2RpdGllenVmYW5nL2xpNDY0NjExNzkvcnQyMDA2MDAwMDAwMDFsMSIsIm9zIjoid2ViIiwidiI6IjAuMSJ9"}49 response = requests.get(url=urls, headers=headers)50 main(response)51 exceptRequestException:52 returnNone53
54
55
56 if __name__=="__main__":57 for i in range(64): #遍历翻页
58 if(i==0):59 urls = "https://bj.lianjia.com/ditiezufang/li46461179/rt200600000001l1/"
60 get_one_page(urls)61 else:62 urls = "https://bj.lianjia.com/ditiezufang/li46461179/rt200600000001l1/".replace("rt","pg"+str(i))63 get_one_page(urls)