请有识之士帮忙看下，好人一生平安：

1 .　爬该网站：网址 https://www.cqggzy.com/xxhz/014001/014001001/zbggjyxx-page.html?keyword=%E6%95%B0%E6%8D%AE，，解密后网址：https://www.cqggzy.com/xxhz/014001/014001001/zbggjyxx-page.html?keyword=数据
２．目标：搜索出‘数据’相关的信息，爬出的搜索信息部分被JS封装，
３．代码如下：

import ssl # 防止验证报错
ssl._create_default_https_context = ssl._create_unverified_context
import urllib.request as ur
import urllib.parse as up
import requests
import re,json
import lxml.etree as le
# import xpath_tool
import pymongo

kw = '数据'
data = {
    'keyword': kw
}
data_url = up.urlencode(data) # encode
url = 'https://www.cqggzy.com/xxhz/014001/014001001/zbggjyxx-page.html?'+data_url
headers = {'User-Agent':'Mozilla/5.0.html (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.html.1271.64 Safari/537.11'}

req = ur.Request(
    url = url,
    headers = headers
)
content = ur.urlopen(req).read().decode('utf-8', 'ignore')
with open('数据.html','w',encoding='utf-8') as f:
    f.write(content)

新增用request.post方法尝试失败：

url_js = 'https://www.cqggzy.com/interface/rest/inteligentSearch/getFullTextData'
headers_js = {
    "Accept": "application/json, text/javascript, */*; q=0.01",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept-Language": "zh-CN,zh;q=0.9,en-GB;q=0.8,en;q=0.7",
    "Connection": "keep-alive",
    "Content-Length": "615",
    "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
    "Cookie": "JSESSIONID=139064B5D7DE210BE4B58893B41C2C7F; __jsluid_s=55e35824b3517a59c43c1b750043c288; cookie_www=19398923; Hm_lvt_3b83938a8721dadef0b185225769572a=1614754494,1614777887; Hm_lpvt_3b83938a8721dadef0b185225769572a=1614781676",
    "Host": "www.cqggzy.com",
    "Origin": "https://www.cqggzy.com",
    "Referer": "https://www.cqggzy.com/xxhz/014001/014001001/zbggjyxx-page.html?keyword=%E6%95%B0%E6%8D%AE",
    "Sec-Fetch-Dest": "empty",
    "Sec-Fetch-Mode": "cors",
    "Sec-Fetch-Site": "same-origin",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36",
    "X-Requested-With": "XMLHttpRequest"
}


data_js = {
            "token": "",
            "pn": 0,
            "rn": 18,
            "sdt": "",
            "edt": "",
            "wd": " ",
            "inc_wd": "",
            "exc_wd": "",
            "fields": "title",
            "cnum": "001",
            "sort": {"istop":0,"ordernum":0,"webdate":0,"rowid":0},
            "ssort": "title",
            "cl": 200,
            "terminal": "",
            "condition": [
                {"fieldName": "categorynum", "equal": "014001001", "notEqual": None, "equalList": None, "notEqualList": None,
                 "isLike": True, "likeType": 2},
                {"fieldName": "titlenew", "equal": "数据", "notEqual": None, "equalList": None, "notEqualList": None,
                 "isLike": True,
                 "likeType": 0}],
            "time": None,
            "highlights": "title",
            "statistics": None,
            "unionCondition": [],
            "accuracy": "",
            "noParticiple": "0",
            "searchRange": None,
            "isBusiness": "1"
        }

res=requests.post(url=url_js,headers=headers_js,data=data_js)
print('res:', res)
print('res',res.text)

F12->network->XHR->F5，获得的headers作为headers和form data 作为data

打印结果一个返回500，一个空白

res: <Response [500]>
res:

ᐒ

[Python] 尾递归方式求二叉查找树r中大于x的最小key

1条回答

为你推荐