requests form data 请求 爬虫

抓取某个网站，抓包如下

form data 这个简单，只需要用如下请求即可：

url = "http://www.hebpr.gov.cn/inteligentsearch/rest/inteligentSearch/getFullTextData"

headers = {

    "Host":"www.hebpr.gov.cn",
    "Connection":"keep-alive",
    "Content-Length":"455",
    "Accept":"application/json, text/javascript, */*; q=0.01",
    "X-Requested-With":"XMLHttpRequest",
    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36",
    "Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",
    "Origin":"http://www.hebpr.gov.cn",
    "Referer":"http://www.hebpr.gov.cn/hbggfwpt/jydt/salesPlat.html",
    "Accept-Encoding":"gzip, deflate",
    "Accept-Language":"zh-CN,zh;q=0.9",
    "Cookie":"JSESSIONID=0B5BEF6312E940A0AB4E06644C4B1602; oauthClientId=demoClient; oauthPath=http://127.0.0.1:8000/EpointWebBuilderZw; oauthLoginUrl=http://127.0.0.1:8000/EpointWebBuilderZw/rest/oauth2/authorize?client_id=demoClient&state=a&response_type=code&scope=user&redirect_uri=; oauthLogoutUrl=http://127.0.0.1:8000/EpointWebBuilderZw/rest/oauth2/logout?redirect_uri=; noOauthRefreshToken=f05e845edf4bcac5a038cd422ddb460a; noOauthAccessToken=dc3559e6a5d958f1663e4df62e6965a0; userGuid=-31722750",


}

null = "null"
true = "true"
data = '{"token":"","pn":60,"rn":10,"sdt":"","edt":"","wd":" ","inc_wd":"","exc_wd":"","fields":"title","cnum":"001","sort":"{\"webdate\":0}","ssort":"title","cl":200,"terminal":"","condition":[{"fieldName":"categorynum","equal":"003001","notEqual":null,"equalList":null,"notEqualList":null,"isLike":true,"likeType":2}],"time":null,"highlights":"title","statistics":null,"unionCondition":null,"accuracy":"","noParticiple":"0","searchRange":null,"isBusiness":"1"}'

result = requests.post(url=url, data=data,headers=headers,verify=False).json()
print "result",result

　　

注意事项： webdate 前后的单斜杠换成双斜杠