抓取网址的多个页面时如何创建for循环？

Question

我希望能够创建一个 for 循环来抓取具有多个页面的 url。 我发现了一些这样的例子，但是我的代码需要身份验证，因此我没有共享实际的 url。 我输入了一个显示相同密钥标识符“currentPage=1”的示例 url

因此，对于页面 i 的此示例，它将是 currentPage=i，其中 i 将是 1,2,3,4....

import requests
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry


def requests_retry_session(retries=10,
                           backoff_factor=0.3,
                           status_forcelist=(500, 502, 503, 504),
                           session=None):

    session = session or requests.Session()

    retry = Retry(total=retries,
                  read=retries,
                  connect=retries,
                  backoff_factor=backoff_factor,
                  status_forcelist=status_forcelist)

    adapter = HTTPAdapter(max_retries=retry)
    session.mount("http://", adapter)
    session.mount("https://", adapter)
    return session


import io

import urllib3
import pandas as pd
from requests_kerberos import OPTIONAL, HTTPKerberosAuth

import mwinit2web
a = mwinit2web.get_mwinit_cookie()

urls = https://example-url.com/ABCD/customer.currentPage=1&end

def Scraper(url):
    urllib3.disable_warnings()
    with requests_retry_session() as req:
        resp = req.get(url,
                        timeout=30,
                        verify=False,
                        allow_redirects=True,
                        auth=HTTPKerberosAuth(mutual_authentication=OPTIONAL),
                        cookies=a)


    global df
    data = pd.read_html(resp.text, flavor=None, header=0, index_col=0)
    df = pd.concat(data, sort=False)
    print(df)

s = Scraper(urls)
df

Answer 1

pageCount = 4 #say you have 3 pages
urlsList = []
base = "https://example-url.com/ABCD/customer.currentPage={}&end" #curly braces let you format


for x in range(pageCount)[1:]:
    urlsList.append(base.format(x))

然后您可以将列表传递给您的函数。