asp.net - 如何使用 python 请求和 BeautifulSoup 在 Aspx 动态网站中循环下拉菜单并抓取数据

Question

对于我的问题，我读了这篇文章“request using python to asp.net page”，这也是 Data Scraping, aspx ，我找到了我正在寻找的东西，但还有一些小问题需要解决。

我想抓取一个网站http://up-rera.in/ ，是aspx动态网站。通过单击检查元素网站会抛出一个不同的链接，如下所示:http://upreraportal.cloudapp.net/View_projects.aspx

它正在使用 Aspx

如何循环所有下拉菜单并点击搜索来获取页面内容；例如，我能够抓取阿格拉并能够获取页面详细信息。

由于这是我的学习阶段，因此我避免使用 Selenium 来获取页面详细信息。

这是我的代码:

import requests
from bs4 import BeautifulSoup
import os
import time
import csv

final_data = []

url = "http://upreraportal.cloudapp.net/View_projects.aspx"

headers= {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
          'Content-Type':'application/x-www-form-urlencoded',
          'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}

formfields={'__VIEWSTATE':'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',
            '__VIEWSTATEGENERATOR':'4F1A7E70',
            '__EVENTVALIDATION':'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',
            'ctl00$ContentPlaceHolder1$DdlprojectDistrict':'Agra',
            'ctl00$ContentPlaceHolder1$txtProject':'',
            'ctl00$ContentPlaceHolder1$btnSearch':'Search'}

#here in form details check agra , i am able to scrape one city only,
# how to loop for all cities
r = requests.post(url, data=formfields, headers=headers)
data=r.text

soup = BeautifulSoup(data, "html.parser")

get_list  = soup.find_all('option')   #gets list of all <option> tag
for element in get_list :
    cities = element["value"]
    #final.append(cities)
    #print(final)

get_details = soup.find_all("table", attrs={"id":"ContentPlaceHolder1_GridView1"})

for details in get_details:
    text = details.find_all("tr")[1:]
    for tds in text:
        td = tds.find_all("td")[1]
        rera = td.find_all("span")
        rnumber = ""
        for num in rera:
            rnumber = num.text
            print(rnumber)

Answer 1

尝试下面的代码。它会给你你想要的所有结果。只需要稍微抽动一下即可。我只是从下拉菜单中抓取了不同的名称，并在循环中使用这些名称，以便您可以一一获取所有数据。除了添加几行之外，我没有注意到其他内容。如果将代码包装在函数中，您的代码可能会更好。

顺便说一句，我将两个巨大的字符串放在两个变量中，这样您就不必担心它并使其变得更 slim 。这是更正后的代码:

import requests
from bs4 import BeautifulSoup

url = "http://upreraportal.cloudapp.net/View_projects.aspx"
response = requests.get(url).text
soup = BeautifulSoup(response,"lxml")

VIEWSTATE = soup.select("#__VIEWSTATE")[0]['value']
EVENTVALIDATION = soup.select("#__EVENTVALIDATION")[0]['value']

for title in soup.select("#ContentPlaceHolder1_DdlprojectDistrict [value]")[:-1]:
    search_item = title.text
    # print(search_item)

    headers= {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
              'Content-Type':'application/x-www-form-urlencoded',
              'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}

    formfields = {'__VIEWSTATE':VIEWSTATE,  #Put the value in this variable
                '__VIEWSTATEGENERATOR':'4F1A7E70',
                '__EVENTVALIDATION':EVENTVALIDATION, #Put the value in this variable
                'ctl00$ContentPlaceHolder1$DdlprojectDistrict':search_item, #this is where your city name changes in each iteration
                'ctl00$ContentPlaceHolder1$txtProject':'',
                'ctl00$ContentPlaceHolder1$btnSearch':'Search'}

    #here in form details check agra , i am able to scrape one city only,
    # how to loop for all cities
    res = requests.post(url, data=formfields, headers=headers).text
    soup = BeautifulSoup(res, "html.parser")

    get_list  = soup.find_all('option')   #gets list of all <option> tag
    for element in get_list :
        cities = element["value"]
        #final.append(cities)
        #print(final)

    get_details = soup.find_all("table", attrs={"id":"ContentPlaceHolder1_GridView1"})

    for details in get_details:
        text = details.find_all("tr")[1:]
        for tds in text:
            td = tds.find_all("td")[1]
            rera = td.find_all("span")
            rnumber = ""
            for num in rera:
                rnumber = num.text
                print(rnumber)