106

我尝试构建一个 python 脚本，它发送一个带有参数的 POST 以提取结果。使用提琴手，我提取了我想要的返回请求。该网站仅使用 https。

POST /Services/GetFromDataBaseVersionned HTTP/1.1
Host: www.mywbsite.fr
"Connection": "keep-alive",
"Content-Length": 129,
"Origin": "https://www.mywbsite.fr",
"X-Requested-With": "XMLHttpRequest",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.52 Safari/536.5",
"Content-Type": "application/json",
"Accept": "*/*",
"Referer": "https://www.mywbsite.fr/data/mult.aspx",
"Accept-Encoding": "gzip,deflate,sdch",
"Accept-Language": "fr-FR,fr;q=0.8,en-US;q=0.6,en;q=0.4",
"Accept-Charset": "ISO-8859-1,utf-8;q=0.7,*;q=0.3",
"Cookie": "ASP.NET_SessionId=j1r1b2a2v2w245; GSFV=FirstVisit=; GSRef=https://www.google.fr/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0CHgQFjAA&url=https://www.mywbsite.fr/&ei=FZq_T4abNcak0QWZ0vnWCg&usg=AFQjCNHq90dwj5RiEfr1Pw; HelpRotatorCookie=HelpLayerWasSeen=0; NSC_GSPOUGS!TTM=ffffffff09f4f58455e445a4a423660; GS=Site=frfr; __utma=1.219229010.1337956889.1337956889.1337958824.2; __utmb=1.1.10.1337958824; __utmc=1; __utmz=1.1337956889.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided)"

{"isLeftColumn":false,"lID":-1,"userIpCountryCode":"FR","version":null,"languageCode":"fr","siteCode":"frfr","Quotation":"eu"}

现在我的python脚本：

#!/usr/bin/env python
# -*- coding: iso-8859-1 -*-
import string
import httplib
import urllib2

host = "www.mywbsite.fr/sport/multiplex.aspx"
    params='"isLeftColumn":"false","liveID":"-1","userIpCountryCode":"FR","version":"null","languageCode":"fr","siteCode":"frfr","Quotation":"eu"'

headers = { Host: www.mywbsite.fr,
"Connection": "keep-alive",
"Content-Length": 129,
"Origin": "https://www.mywbsite.fr",
"X-Requested-With": "XMLHttpRequest",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.52 Safari/536.5",
"Content-Type": "application/json",
"Accept": "*/*",
"Referer": "https://www.mywbsite.fr/data/mult.aspx",
"Accept-Encoding": "gzip,deflate,sdch",
"Accept-Language": "fr-FR,fr;q=0.8,en-US;q=0.6,en;q=0.4",
"Accept-Charset": "ISO-8859-1,utf-8;q=0.7,*;q=0.3",
"Cookie": "ASP.NET_SessionId=j1r1b2a2v2w245; GSFV=FirstVisit=;     GSRef=https://www.google.fr/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0CHgQFjAA&url=https://www.mywbsite.fr/&ei=FZq_T4abNcak0QWZ0vnWCg&usg=AFQjCNHq90dwj5RiEfr1Pw; HelpRotatorCookie=HelpLayerWasSeen=0; NSC_GSPOUGS!TTM=ffffffff09f4f58455e445a4a423660; GS=Site=frfr; __utma=1.219229010.1337956889.1337956889.1337958824.2; __utmb=1.1.10.1337958824; __utmc=1; __utmz=1.1337956889.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided)"

}

url = "/Services/GetFromDataBaseVersionned"

# POST the request
conn = httplib.HTTPConnection(host,port=443)
conn.request("POST",url,params,headers)
response = conn.getresponse()

data = response.read()
print data

但是当我运行我的脚本时，我有这个错误：

socket.gaierror: [Errno -2] Name or service not known
4

3 回答 3

125

非常感谢您链接到请求模块。简直太完美了。下面是我的问题的解决方案。

import requests
import json

url = 'https://www.mywbsite.fr/Services/GetFromDataBaseVersionned'
payload = {
    "Host": "www.mywbsite.fr",
    "Connection": "keep-alive",
    "Content-Length": 129,
    "Origin": "https://www.mywbsite.fr",
    "X-Requested-With": "XMLHttpRequest",
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.52 Safari/536.5",
    "Content-Type": "application/json",
    "Accept": "*/*",
    "Referer": "https://www.mywbsite.fr/data/mult.aspx",
    "Accept-Encoding": "gzip,deflate,sdch",
    "Accept-Language": "fr-FR,fr;q=0.8,en-US;q=0.6,en;q=0.4",
    "Accept-Charset": "ISO-8859-1,utf-8;q=0.7,*;q=0.3",
    "Cookie": "ASP.NET_SessionId=j1r1b2a2v2w245; GSFV=FirstVisit=; GSRef=https://www.google.fr/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0CHgQFjAA&url=https://www.mywbsite.fr/&ei=FZq_T4abNcak0QWZ0vnWCg&usg=AFQjCNHq90dwj5RiEfr1Pw; HelpRotatorCookie=HelpLayerWasSeen=0; NSC_GSPOUGS!TTM=ffffffff09f4f58455e445a4a423660; GS=Site=frfr; __utma=1.219229010.1337956889.1337956889.1337958824.2; __utmb=1.1.10.1337958824; __utmc=1; __utmz=1.1337956889.1.1.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided)"
}
# Adding empty header as parameters are being sent in payload
headers = {}
r = requests.post(url, data=json.dumps(payload), headers=headers)
print(r.content)
于 2012-05-28T10:06:26.120 回答
106

如果我们想将自定义 HTTP 标头添加到POST 请求，我们必须通过字典将它们传递给 headers 参数。

这是一个带有非空正文和标头的示例：

import requests
import json

url = 'https://somedomain.com'
body = {'name': 'Maryja'}
headers = {'content-type': 'application/json'}

r = requests.post(url, data=json.dumps(body), headers=headers)

来源

于 2019-02-02T14:01:56.280 回答
5

要使用 POST 请求而不是 GET 请求urllib2，您需要指定空数据，例如：

import urllib2
req = urllib2.Request("http://am.domain.com:8080/openam/json/realms/root/authenticate?authIndexType=Module&authIndexValue=LDAP")
req.add_header('X-OpenAM-Username', 'demo')
req.add_data('')
r = urllib2.urlopen(req)
于 2019-11-26T08:22:06.887 回答