从网站python中提取所有pdf文件[关闭]

Question

关闭。 这个问题需要更加集中。 它目前不接受答案。

---

想改进这个问题？ 更新问题，使其仅通过编辑此帖子专注于一个问题。

2天前关闭。

改进这个问题

使用 Python，我想获取每个查询的最后一页。 我怎样才能用我的代码做到这一点？

from bs4 import BeautifulSoup 
import requests, lxml, urllib.request
from random import randint
from time import sleep
from urllib.parse import urljoin
import re
import os
from datetime import date


folder_location = r'./ASN Documents'
if not os.path.exists(folder_location):os.mkdir(folder_location)

我想用这些查询提取 pdf query_list=["maintenance","fukushima"]

url_asn="https://www.asn.fr/recherche?filter_year[from]={}&filter_year[to]={}&limit=50&&search_text={}&sort_type=date&page={}"

while True:
    for query in query_list:
        for page in range(1, last_page, 1):
            format_url=url_asn.format(date.today().year - 10, date.today().year, query, page)
            url=format_url.replace(" ", "%20")
            req=requests.get(url)
            soup = BeautifulSoup(req.content, 'html.parser')
            for link in soup.findAll("a", class_="Teaser-titleLink"):
                if link['href'] != '.pdf':
                    jk="https://www.asn.fr/"+link['href']
                    reqHTML = requests.get(jk):
                    soupHTML=BeautifulSoup(reqHTML.content, 'html.parser')
                    for pdf in soupHTML.select("a[href$='.pdf']"):
                        filename = os.path.join(folder_location, link.getText()
                        .rstrip()
                        .replace("%20", " "))
                        with open(f"{filename}.pdf", 'wb') as f:
                            f.write(requests.get(urljoin(url, link['href'])).content) 

Answer 1

要查找最后一页，您可以使用find_all然后访问倒数第二个索引：

import requests
from bs4 import BeautifulSoup

url = 'https://www.asn.fr/recherche?filter_year[from]=2012&filter_year[to]=2022&limit=50&&search_text=maintenance&sort_type=date&page=1'
rsp = requests.get(url)
soup = BeautifulSoup(rsp.content, 'html.parser')

int(soup.find_all("a", {"class": "page-link"})[-2].text)