python - Scrapy 爬取带有 PostBack 数据 javascript url 的页面不会改变

Question

我正在通过 Scrapy 使用 ASP.NET 编程爬取一些目录。

要抓取的页面是这样编码的:

javascript:__doPostBack('MoreInfoListZbgs1$Pager','X')

其中 X 是 1 到 180 之间的整数。问题是当我单击下一页或任何页面时，url 保持不变。我在下面写下了一些代码，它们只能提取第一页中的每个链接。

# -*- coding: utf-8 -*-
import scrapy
from bs4 import BeautifulSoup
import re
from scrapy.http import FormRequest
import js2xml
import requests
from datetime import datetime


class nnggzySpider(scrapy.Spider):

    name = 'nnggzygov'
    start_urls = [
        'https://www.nnggzy.org.cn/gxnnzbw/showinfo/zbxxmore.aspx?categorynum=001004001'
    ]

    base_url = 'https://www.nnggzy.org.cn'


    custom_settings = {
        'LOG_LEVEL': 'ERROR'
    }

    def parse(self, response):
        _response = response.text
        self.data = {}
        soup = BeautifulSoup(response.body, 'html.parser')
        tags = soup.find_all('a', href=re.compile(r"InfoDetail"))

        # 获取翻页参数
        __VIEWSTATE = re.findall(r'id="__VIEWSTATE" value="(.*?)" />', _response)
        A = __VIEWSTATE[0]
        # print(A)
        __EVENTTARGET = 'MoreInfoListZbgs1$Pager'
        B = __EVENTTARGET
        __CSRFTOKEN = re.findall(r'id="__CSRFTOKEN" value="(.*?)" />', _response)
        C = __CSRFTOKEN
        page_num = re.findall(r'title="转到第(.*?)页"', _response)
        max_page = page_num[-1]

        content = {
            '__VIEWSTATE': A,
            '__EVENTTARGET': B,
            '__CSRFTOKEN': C,
            'page_num': max_page
        }
        infoid = re.findall(r'InfoID=(.*?)&CategoryNum', _response)
        print(infoid)
        yield scrapy.Request(url=response.url, callback=self.parse_detail, meta={"data": content})

    def parse_detail(self, response):
        max_page = response.meta['data']['page_num']
        for i in range(2, int(max_page)):
            data = {
                '__CSRFTOKEN': '{}'.format(response.meta['data']['__CSRFTOKEN']),
                '__VIEWSTATE': '{}'.format(response.meta['data']['__VIEWSTATE']),
                '__EVENTTARGET': 'MoreInfoListZbgs1$Pager',
                '__EVENTARGUMENT': '{}'.format(i),
                # '__VIEWSTATEENCRYPTED': '',
                # 'txtKey': ''
            }
            yield scrapy.FormRequest(url=response.url, callback=self.parse, formdata=data, method="POST", dont_filter=True)

谁能帮我解决这个问题？

Answer 1

看起来上述网站的分页是通过发送带有如下格式数据的 POST 请求完成的:

{
    "__CSRFTOKEN": ...,
    "__VIEWSTATE": ...,
    "__EVENTTARGET": "MoreInfoListZbgs1$Pager",
    "__EVENTARGUMENT": page_number,
    "__VIEWSTATEENCRYPTED": "",
    "txtKey": ""
}