Python 3 : how to scrape research results from a website using CSFR?

Question

我正在尝试抓取列出法国众贷金融科技网站的研究成果:https://www.orias.fr/web/guest/search

手动执行此操作，我在单选按钮中选择 (IFP)，然后它为我提供 13 个结果页，每页 10 个结果。每个结果都有一个超链接，我还想从决赛表中获取信息。

我的主要问题似乎来自CSRF，在结果地址中，有:p_auth=8mxk0SsK因此，我不能简单地通过将链接中的“p=2”更改为“p=13”来循环浏览结果页面: https://www.orias.fr/search?p_auth=8mxk0SsK&p_p_id=intermediaryDetailedSearch_WAR_oriasportlet&p_p_lifecycle=1&p_p_state=normal&p_p_mode=view&p_p_col_id=column-1&p_p_col_count=1&_intermediaryDetailedSearch_WAR_oriasportlet_myaction=fullSearch

如果我尝试手动使用 VPN，网站地址会变得“稳定”: https://www.orias.fr/search?p_p_id=intermediaryDetailedSearch_WAR_oriasportlet&p_p_lifecycle=0&p_p_state=normal&p_p_mode=view&p_p_col_id=column-1&p_p_col_count=1&_intermediaryDetailedSearch_WAR_oriasportlet_d-16544-p=1&_intermediaryDetailedSearch_WAR_oriasportlet_implicitModel=true&_intermediaryDetailedSearch_WAR_oriasportlet_spring_render=searchResult

所以我尝试在Python代码中使用它:

    import requests
    from bs4 import BeautifulSoup

    k = 1
    % test k from 1 to 13


    url = "http://www.orias.fr/search?p_p_id=intermediaryDetailedSearch_WAR_oriasportlet&p_p_lifecycle=0&p_p_state=normal&p_p_mode=view&p_p_col_id=column-1&p_p_col_count=1&_intermediaryDetailedSearch_WAR_oriasportlet_d-16544-p="  + str(k) + "&_intermediaryDetailedSearch_WAR_oriasportlet_implicitModel=true&_intermediaryDetailedSearch_WAR_oriasportlet_spring_render=searchResult"
    response = requests.get(url, proxies=proxies) # 200 ment it went through    
    soup = BeautifulSoup(response.text, "html.parser")

    table = soup.find('table', attrs={'class':'table table-condensed table-striped table-bordered'})
    table_rows = table.find_all('tr')

    l = []
    for tr in table_rows:
        td = tr.find_all('td')
        row = [tr.text for tr in td]
        l.append(row)

这不像在网络浏览器中那样工作，它只是提供一个页面，就好像没有请求结果一样。你知道如何让它发挥作用吗？

Answer 1

我会在循环期间更改发布请求中的页面参数。执行初始请求以查明页数

from bs4 import BeautifulSoup as bs
import requests, re, math
import pandas as pd

headers = {
    'Content-Type': 'application/x-www-form-urlencoded',
    'User-Agent': 'Mozilla/5.0',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'Referer': 'https://www.orias.fr/web/guest/search'
}

params = [['p_p_id', 'intermediaryDetailedSearch_WAR_oriasportlet'],
    ['p_p_lifecycle', '0'],
    ['p_p_state', 'normal'],
    ['p_p_mode', 'view'],
    ['p_p_col_id', 'column-1'],
    ['p_p_col_count', '1'],
    ['_intermediaryDetailedSearch_WAR_oriasportlet_d-16544-p', '1'],
    ['_intermediaryDetailedSearch_WAR_oriasportlet_implicitModel', 'true'],
    ['_intermediaryDetailedSearch_WAR_oriasportlet_spring_render', 'searchResult']]

data = {
  'searchString': '',
  'address': '',
  'zipCodeOrCity': '',
  '_coa': 'on',
  '_aga': 'on',
  '_ma': 'on',
  '_mia': 'on',
  '_euIAS': 'on',
  'mandatorDenomination': '',
  'wantsMandator': 'no',
  '_cobsp': 'on',
  '_mobspl': 'on',
  '_mobsp': 'on',
  '_miobsp': 'on',
  '_bankActivities': '1',
  '_euIOBSP': 'on',
  '_cif': 'on',
  '_alpsi': 'on',
  '_cip': 'on',
  'ifp': 'true',
  '_ifp': 'on',
  'submit': 'Search'
}

p = re.compile(r'(\d+)\s+intermediaries found')

with requests.Session() as s:
    r= requests.post('https://www.orias.fr/search', headers=headers, params= params, data=data)
    soup = bs(r.content, 'lxml') 
    num_results = int(p.findall(r.text)[0])
    results_per_page = 20
    num_pages = math.ceil(num_results/results_per_page)
    df = pd.read_html(str(soup.select_one('.table')))[0]

    for i in range(2, num_pages + 1):
        params[6][1] = str(i)
        r= requests.post('https://www.orias.fr/search', headers=headers, params= params, data=data)
        soup = bs(r.content, 'lxml') 
        df_next = pd.read_html(str(soup.select_one('.table')))[0]
        df = pd.concat([df, df_next])

df.drop('Unnamed: 6', axis = 1, inplace = True)
df.reset_index(drop=True) 

<小时/>

检查:

print(len(df['Siren Number'].unique()))
#245