python urllib post请求负载的问题

cqwcns

查看浏览器负载是这样的：


我的代码是这样的：

[Python] 纯文本查看 复制代码

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import re
import urllib.request

# 基本配置
baseUrl = "https://appmail.mail.10086.cn/s?func=mbox:listMessages&sid=00Y1ODcyNTQ5OTAwMTYzMjQ402FAAAE7000003&&comefrom=54&cguid=1537104900668"
post_data = {
    'func': 'mbox:listMessages',
    'sid': '00Y1ODcyNTQ5OTAwMTYzMjQ402FAAAE7000003',
    'comefrom': 54,
    'cguid': 1537104900668
}
header = {
    'cookie': 'CmLocation=200|200; CmProvid=gd; WT_FPC=id=2a77ac12a84388a29ce1656819455873:lv=1656819466795:ss=1656819855873; UM_distinctid=181c6f0bd88211-08db9745174c56-4a617f5c-15f900-181c6f0bdcc16b; _139_login_agreement=1; Login_UserNumber=MTM1NTM2ODcyOTk=; _139_login_version=60; S_DEVICE_TOKEN=5374a4b7a37c442aa88a984b564f8815; DEVICE_INFO_DIGEST=a52b58f888209e853dceb76e71c6b9793; a_l=1673050632000|4995576828; a_l2=1673050632000|12|MTM1NTM2O88yOTl8MjAyMy0wMS0wNyAw88oxNzoxMnxvL1Yrc0JTQ1IybXh2SzM1OEd4L0VMdTQ0U0lwNTd2L0VvdnJrbU1wcHl3OTNlYXNwSEl88Wo5TjRUbWRwRXVPbTB6QVUrb0NWWk0xTE5Bb25LZEFwdz09fGI4MjQwY2Y5MWFiOWUxMGZlYjM5MDI2Nzg1ODA4OTI2; RMKEY=409cedd23bd32b49; cookiepartid1688=12; ut1688=2; cookiepartid=12; UserData={}; SkinPath21688=skin_skyBlue; rmUin1688=479121018; provCode1688=1; areaCode1688=16; loginProcessFlag=; Os_SSo_Sid=00Y1ODcyNTQ5OTAwMTYzMjQ402FCCAE7000003; welcome=s%3AKdftUXiorBuX5blKxNyLzlfuljVvYcXF.yJaX8CZrQVW48O%2BA2xb9LPuT2GipD2Yvn3IaiAlxgaE',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.114 Safari/537.36 Edg/103.0.1264.62'
}

def get_html(url):
    data = urllib.parse.urlencode(post_data).encode('utf-8')
    request = urllib.request.Request(
        url, headers=header, data=data, method='POST')
    res = urllib.request.urlopen(request).read().decode('utf-8')
    print(res)


if __name__ == '__main__':
    get_html(baseUrl)

我的代码返回错误是这样的：


从请求负载的信息来看，这个非常关键，决定了从第几条开始读和读多少条等。

[HTML] 纯文本查看 复制代码

<object>
  <int name="fid">1</int>
  <string name="order">receiveDate</string>
  <string name="desc">1</string>
  <int name="start">101</int>
  <int name="total">100</int>
  <string name="topFlag">curr_task</string>
  <int name="sessionEnable">2</int>
  <int name="encodeflag">1</int>
</object>

但这个又不是一个键值对，我不知道怎么传值。


所以，请教一下，这种情况，传递这个请求负载代码应该怎么写？感谢指教。

神枪泡泡丶

post_data 应该放的东西是 请求负载里的，url里的参数放的是 查询字符串参数里的东西。前者错了。构造方式参考标头里的 Content-type

xiaojie96528

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import re
import urllib.request

# 基本配置
baseUrl = "https://appmail.mail.10086.cn/s?func=mbox:listMessages&sid=00Y1ODcyNTQ5OTAwMTYzMjQ402FAAAE7000003&&comefrom=54&cguid=1537104900668"
post_data = "<object>
  <int name="fid">1</int>
  <string name="order">receiveDate</string>
  <string name="desc">1</string>
  <int name="start">101</int>
  <int name="total">100</int>
  <string name="topFlag">curr_task</string>
  <int name="sessionEnable">2</int>
  <int name="encodeflag">1</int>
</object>"
header = {
    'cookie': 'CmLocation=200|200; CmProvid=gd; WT_FPC=id=2a77ac12a84388a29ce1656819455873:lv=1656819466795:ss=1656819855873; UM_distinctid=181c6f0bd88211-08db9745174c56-4a617f5c-15f900-181c6f0bdcc16b; _139_login_agreement=1; Login_UserNumber=MTM1NTM2ODcyOTk=; _139_login_version=60; S_DEVICE_TOKEN=5374a4b7a37c442aa88a984b564f8815; DEVICE_INFO_DIGEST=a52b58f888209e853dceb76e71c6b9793; a_l=1673050632000|4995576828; a_l2=1673050632000|12|MTM1NTM2O88yOTl8MjAyMy0wMS0wNyAw88oxNzoxMnxvL1Yrc0JTQ1IybXh2SzM1OEd4L0VMdTQ0U0lwNTd2L0VvdnJrbU1wcHl3OTNlYXNwSEl88Wo5TjRUbWRwRXVPbTB6QVUrb0NWWk0xTE5Bb25LZEFwdz09fGI4MjQwY2Y5MWFiOWUxMGZlYjM5MDI2Nzg1ODA4OTI2; RMKEY=409cedd23bd32b49; cookiepartid1688=12; ut1688=2; cookiepartid=12; UserData={}; SkinPath21688=skin_skyBlue; rmUin1688=479121018; provCode1688=1; areaCode1688=16; loginProcessFlag=; Os_SSo_Sid=00Y1ODcyNTQ5OTAwMTYzMjQ402FCCAE7000003; welcome=s%3AKdftUXiorBuX5blKxNyLzlfuljVvYcXF.yJaX8CZrQVW48O%2BA2xb9LPuT2GipD2Yvn3IaiAlxgaE',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.114 Safari/537.36 Edg/103.0.1264.62'
    'Content-Type':'这里请填写网页原先请求头内的值'
}

def get_html(url):
    data = urllib.parse.urlencode(post_data).encode('utf-8')
    request = urllib.request.Request(
        url, headers=header, data=data, method='POST')
    res = urllib.request.urlopen(request).read().decode('utf-8')
    print(res)


if __name__ == '__main__':
    get_html(baseUrl)

UndCover

请求负载功能还没有用过，学习一下

很快再相见123

配置一下请求头，是可以的
'Cookie': '你的Cookie',
'Content-Type': 'application/xml'

from requests import post as requests_post

def request_mail_receiver():
    base_url = 'https://appmail.mail.10086.cn/s?func=mbox:listMessages&sid=00Y1ODcyNTQ5OTAwMTYzMjQ402FAAAE7000003&&comefrom=54&cguid=153710490066'
    application_xml_data = '''
    <object>
      <int name="fid">1</int>
      <string name="order">receiveDate</string>
      <string name="desc">1</string>
      <int name="start">1</int>
      <int name="total">20</int>
      <string name="topFlag">curr_task</string>
      <int name="sessionEnable">2</int>
      <int name="encodeflag">1</int>
    </object>
    '''
    cr_header = {
        'Cookie': '你的Cookie',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
        'Content-Type': 'application/xml'
    }
    cr_response = requests_post(base_url, data=application_xml_data,headers=cr_header).content.decode('UTF-8')
    print(cr_response)

if __name__ == '__main__':
    print('Hello')
    request_mail_receiver()

xd223

学习了，增加经验

Ylvan

刚开始学爬虫，看不懂，顶一下

三滑稽甲苯

data="<数据>"
这样子就好了

JKTeller

学到了！！