python使用pdfplumber库一键提取pdf中的所有超链接

pip install pdfplumber

import pdfplumber


with pdfplumber.open(r'./data/test.pdf') as pdf_info:
    for page in pdf_info.pages:
        links = page.hyperlinks
    print(links)

import pdfplumber


def get_links(file_path):
    res_links = []
    with pdfplumber.open(file_path) as pdf_info:
        page_number = 0
        for page in pdf_info.pages:
            page_number += 1
            links = page.hyperlinks
            if links:
                for link in links:
                    res_link = link.get('uri')
                    res_links.append(res_link)
                print(f'第{page_number}页，共有{len(links)}个超链接！')
            else:
                print(f'第{page_number}页，不存在超链接!')
    return res_links


if __name__=="__main__":
    # 文件路径为 pdf 完整路径
    res_links = get_links('data/FCC_all.pdf')
    print(res_links)

import pdfplumber
def extract_links(pdf_path):
    all_links = []
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            page_links = page.hyperlinks
            if page_links:
                for link in page_links:
                    # 每个 link 是一个字典，'uri' 键存储了目标网址
                    uri = link.get('uri')
                    if uri:
                        all_links.append(uri)
    return all_links
if __name__ == "__main__":
    links = extract_links("你的文件.pdf")
    for link in links:
        print(link)

for i, page in enumerate(pdf.pages):
    links = page.hyperlinks
    if links:
        print(f"第 {i+1} 页 有 {len(links)} 个链接")
        for link in links:
            print(f"  - {link.get('uri')}")
    else:
        print(f"第 {i+1} 页 没有链接")

if 'uri' in link:
    print(f"网页链接: {link['uri']}")
elif 'page' in link:
    print(f"内部链接: 第 {link['page']} 页")
elif 'nameddest' in link:
    print(f"命名目标: {link['nameddest']}")

with pdfplumber.open("encrypted.pdf", password="你的密码") as pdf:
    # ... 正常提取链接