python - 下载多个 PDF 时出现问题

Question

运行以下代码后，我无法打开下载的 PDF。尽管代码运行成功，但下载的 PDF 文件已损坏。

我的计算机的错误消息是

Unable to open file. it may be damaged or in a format Preview doesn't recognize.

为什么它们会损坏以及如何解决这个问题？

import os
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup

url = "https://github.com/sonhuytran/MIT8.01SC.2010F/tree/master/References/University%20Physics%20with%20Modern%20Physics%2C%2013th%20Edition%20Solutions%20Manual"

#If there is no such folder, the script will create one automatically
folder_location = r'/Users/rahelmizrahi/Desktop/ Physics_Solutions'
if not os.path.exists(folder_location):os.mkdir(folder_location)

response = requests.get(url)
soup= BeautifulSoup(response.text, "html.parser")     
for link in soup.select("a[href$='.pdf']"):

    filename = os.path.join(folder_location,link['href'].split('/')[-1])
    with open(filename, 'wb') as f:
        f.write(requests.get(urljoin(url,link['href'])).content) 

Answer 1

此问题是当您需要 'raw' 链接时，您正在请求 github 'blob' 中的链接:

'/sonhuytran/MIT8.01SC.2010F/blob/master/References/University%20Physics%20with%20Modern%20Physics%2C%2013th%20Edition%20Solutions%20Manual/A01_YOUN6656_09_ISM_FM.pdf'

但你想要:

'/sonhuytran/MIT8.01SC.2010F/raw/master/References/University%20Physics%20with%20Modern%20Physics%2C%2013th%20Edition%20Solutions%20Manual/A01_YOUN6656_09_ISM_FM.pdf'

所以只需调整一下即可。完整代码如下:

import os
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup

url = "https://github.com/sonhuytran/MIT8.01SC.2010F/tree/master/References/University%20Physics%20with%20Modern%20Physics%2C%2013th%20Edition%20Solutions%20Manual"

#If there is no such folder, the script will create one automatically
folder_location = r'/Users/rahelmizrahi/Desktop/Physics_Solutions'
if not os.path.exists(folder_location):os.mkdir(folder_location)

response = requests.get(url)
soup= BeautifulSoup(response.text, "html.parser")     
for link in soup.select("a[href$='.pdf']"):
    pdf_link = link['href'].replace('blob','raw')
    pdf_file = requests.get('https://github.com' + pdf_link)
    filename = os.path.join(folder_location,link['href'].split('/')[-1])
    with open(filename, 'wb') as f:
        f.write(pdf_file.content)