天天看點

python找房源_python 抓取房源資訊

importrequestsfrom bs4 importBeautifulSoupimportip_list#消息頭#headers ={#"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",#"Accept-Encoding":"gzip, deflate, br",#"Accept-Language":"zh-CN,zh;q=0.9",#"Cache-Control":"max-age=0",#"Connection":"keep-alive",#"Cookie":"TS013af1c1=01ef8f99f1d0871b269c53340fa6269029504a80c4e2e4fb5f8c141dc3ea1889dfe9b73e3546aaef50810eb7137614f90423824a3a; _gscu_415563124=710350909btrml20; _gscbrs_415563124=1; TS01dde381_77=087968f3e8ab280075ffa9551835e2b3bc9a0a6ef1f753105fc148025ab082fd79a1cb86cc3a8f52e22695c031dd504308dd5f77e7823800bc61bb50494d8e87319bf3b42d4db90a536ed3feb83a77f2f122231d05b1d9d2348a3ef88a547a3a4fa01ac0c30c12acae8ea546e6c1a1ba; TSf97de9a7_76=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; TSPD_101=087968f3e8ab2800694c407f83260b5fb36f147a01070c43e22a21076b5ec514c7b53bce88b8138a25acd182ef87b3ba:087968f3e8ab2800694c407f83260b5fb36f147a01070c43e22a21076b5ec514c7b53bce88b8138a25acd182ef87b3ba08ef9bf94f06300055e7cf7b71c21fcf57bb0d7a08e541b632d1e81bc2b89a1a0b150eb4c70f05a351fc3a1b4aa2c87583b1593295915bf8; a6c1b8e3d8ee43f7b55efdb3b44bd46e=WyIzNDA2NzQ2MzE0Il0; TS01dde381=01ef8f99f13c1ae3080e65ae71621810e05b79c0c6aa9bdd4bdd59420bc12c88c9cf07ae6c9dbbd39b34b715438e2a022c50ce917f; TSf97de9a7_27=087968f3e8ab2000afda1f036834422803e5ea6f78d56a8329a6c70c885298f80c660dbeab022de90855e1bd82092000ce04d01001dd1ea60427ae89da80b6ff03d8eafda5efd5e059e62400b4741136",#"Host":"www.12309.gov.cn",#"If-None-Match":'W/"10d1c-m2GHDG7mOl/LWWDK4ZcVfpV31es"',#"Sec-Fetch-Mode":"navigate",#"Sec-Fetch-Site":"none",#"Sec-Fetch-User":"?1",#"Upgrade-Insecure-Requests":"1",#"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36",#}

headers ={}#post請求發送json

defpostUrl(url,json_data):

result= requests.post(url ,json = json_data,headers=headers )returnresult.json()#post請求發送json

defgetUrlJson(url):

result= requests.get(url ,headers=headers )returnresult.json()defgetUrl(url):"""url傳回BeautifulSoup對象"""

#proxies = ip_list.get_ip_list_random()#代理ip

#print(proxies)

#content = requests.get(url,headers=headers,proxies=proxies).content

content = requests.get(url,headers=headers).content

soup= BeautifulSoup(content,"html.parser")return soup