{"id":1026592,"date":"2024-12-31T10:43:55","date_gmt":"2024-12-31T02:43:55","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1026592.html"},"modified":"2024-12-31T10:43:58","modified_gmt":"2024-12-31T02:43:58","slug":"pdf%e6%96%87%e6%a1%a3%e5%9c%a8python%e4%b8%ad%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1026592.html","title":{"rendered":"pdf\u6587\u6863\u5728python\u4e2d\u5982\u4f55\u722c\u53d6"},"content":{"rendered":"

\"pdf\u6587\u6863\u5728python\u4e2d\u5982\u4f55\u722c\u53d6\"<\/p>\n

\u5728Python\u4e2d\u722c\u53d6PDF\u6587\u6863<\/strong>\uff0c\u6709\u591a\u79cd\u65b9\u6cd5\u548c\u5de5\u5177\u53ef\u4ee5\u4f7f\u7528\uff0c\u5305\u62ecrequests\u5e93\u3001BeautifulSoup\u5e93\u3001PyPDF2\u5e93\u3001pdfminer\u5e93\u3001Selenium\u5e93<\/strong>\u7b49\u3002\u4e3a\u4e86\u8be6\u7ec6\u63cf\u8ff0\u5176\u4e2d\u4e00\u79cd\u65b9\u6cd5\uff0c\u6211\u4eec\u5c06\u91cd\u70b9\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528requests\u5e93<\/strong>\u548cBeautifulSoup\u5e93<\/strong>\u6765\u4e0b\u8f7dPDF\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528PyPDF2\u5e93<\/strong>\u6765\u8bfb\u53d6PDF\u5185\u5bb9\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b89\u88c5\u5fc5\u8981\u7684\u5e93<\/h2>\n<\/p>\n

\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86\u6240\u9700\u7684Python\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install requests beautifulsoup4 PyPDF2<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Requests\u5e93\u548cBeautifulSoup\u5e93\u722c\u53d6PDF\u6587\u4ef6<\/h2>\n<\/p>\n
1\u3001\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u89e3\u6790HTML<\/h3>\n<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528requests<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u4f7f\u7528BeautifulSoup<\/code>\u5e93\u89e3\u6790HTML\u6587\u6863\u3002\u8fd9\u5c06\u5e2e\u52a9\u6211\u4eec\u627e\u5230\u7f51\u9875\u4e2d\u6240\u6709\u7684PDF\u94fe\u63a5\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
def get_pdf_links(url):<\/p>\n
    response = requests.get(url)<\/p>\n
    soup = BeautifulSoup(response.content, 'html.parser')<\/p>\n
    pdf_links = []<\/p>\n
    for link in soup.find_all('a', href=True):<\/p>\n
        href = link['href']<\/p>\n
        if href.endswith('.pdf'):<\/p>\n
            pdf_links.append(href)<\/p>\n
    return pdf_links<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
pdf_links = get_pdf_links(url)<\/p>\n
print(f'Found {len(pdf_links)} PDF links')<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4e0b\u8f7dPDF\u6587\u4ef6<\/h3>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u904d\u5386\u6240\u6709\u627e\u5230\u7684PDF\u94fe\u63a5\uff0c\u5e76\u4f7f\u7528requests<\/code>\u5e93\u4e0b\u8f7d\u8fd9\u4e9bPDF\u6587\u4ef6\u3002<\/p>\n<\/p>\n
def download_pdfs(pdf_links, download_folder):<\/p>\n
    for link in pdf_links:<\/p>\n
        pdf_response = requests.get(link)<\/p>\n
        pdf_name = link.split('\/')[-1]<\/p>\n
        with open(f'{download_folder}\/{pdf_name}', 'wb') as pdf_file:<\/p>\n
            pdf_file.write(pdf_response.content)<\/p>\n
        print(f'Downloaded {pdf_name}')<\/p>\n
download_folder = 'pdfs'<\/p>\n
download_pdfs(pdf_links, download_folder)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528PyPDF2\u5e93\u8bfb\u53d6PDF\u5185\u5bb9<\/h2>\n<\/p>\n
1\u3001\u5b89\u88c5PyPDF2\u5e93<\/h3>\n<\/p>\n
\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86PyPDF2<\/code>\u5e93\uff0c\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\uff1a<\/p>\n<\/p>\n
pip install PyPDF2<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bfb\u53d6PDF\u6587\u4ef6\u5185\u5bb9<\/h3>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u4f7f\u7528PyPDF2<\/code>\u5e93\u8bfb\u53d6\u4e0b\u8f7d\u7684PDF\u6587\u4ef6\u5185\u5bb9\u3002<\/p>\n<\/p>\n
import PyPDF2<\/p>\n
def read_pdf(file_path):<\/p>\n
    with open(file_path, 'rb') as file:<\/p>\n
        reader = PyPDF2.PdfFileReader(file)<\/p>\n
        num_pages = reader.numPages<\/p>\n
        content = ''<\/p>\n
        for page_num in range(num_pages):<\/p>\n
            page = reader.getPage(page_num)<\/p>\n
            content += page.extract_text()<\/p>\n
    return content<\/p>\n
pdf_file_path = 'pdfs\/example.pdf'<\/p>\n
pdf_content = read_pdf(pdf_file_path)<\/p>\n
print(pdf_content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u6574\u5408\u4ee3\u7801<\/h2>\n<\/p>\n
\u5c06\u4e0a\u8ff0\u6b65\u9aa4\u6574\u5408\u5230\u4e00\u4e2a\u5b8c\u6574\u7684Python\u811a\u672c\u4e2d\uff0c\u4ee5\u5b9e\u73b0\u4ece\u7f51\u9875\u722c\u53d6PDF\u6587\u4ef6\u5e76\u8bfb\u53d6\u5176\u5185\u5bb9\u7684\u529f\u80fd\u3002<\/p>\n<\/p>\n
import requests<\/p>\n
from bs4 import BeautifulSoup<\/p>\n
import PyPDF2<\/p>\n
import os<\/p>\n
def get_pdf_links(url):<\/p>\n
    response = requests.get(url)<\/p>\n
    soup = BeautifulSoup(response.content, 'html.parser')<\/p>\n
    pdf_links = []<\/p>\n
    for link in soup.find_all('a', href=True):<\/p>\n
        href = link['href']<\/p>\n
        if href.endswith('.pdf'):<\/p>\n
            pdf_links.append(href)<\/p>\n
    return pdf_links<\/p>\n
def download_pdfs(pdf_links, download_folder):<\/p>\n
    if not os.path.exists(download_folder):<\/p>\n
        os.makedirs(download_folder)<\/p>\n
    for link in pdf_links:<\/p>\n
        pdf_response = requests.get(link)<\/p>\n
        pdf_name = link.split('\/')[-1]<\/p>\n
        with open(f'{download_folder}\/{pdf_name}', 'wb') as pdf_file:<\/p>\n
            pdf_file.write(pdf_response.content)<\/p>\n
        print(f'Downloaded {pdf_name}')<\/p>\n
def read_pdf(file_path):<\/p>\n
    with open(file_path, 'rb') as file:<\/p>\n
        reader = PyPDF2.PdfFileReader(file)<\/p>\n
        num_pages = reader.numPages<\/p>\n
        content = ''<\/p>\n
        for page_num in range(num_pages):<\/p>\n
            page = reader.getPage(page_num)<\/p>\n
            content += page.extract_text()<\/p>\n
    return content<\/p>\n
url = 'http:\/\/example.com'<\/p>\n
download_folder = 'pdfs'<\/p>\n
pdf_links = get_pdf_links(url)<\/p>\n
print(f'Found {len(pdf_links)} PDF links')<\/p>\n
download_pdfs(pdf_links, download_folder)<\/p>\n
for pdf_name in os.listdir(download_folder):<\/p>\n
    pdf_path = os.path.join(download_folder, pdf_name)<\/p>\n
    content = read_pdf(pdf_path)<\/p>\n
    print(f'Content of {pdf_name}:')<\/p>\n
    print(content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5904\u7406\u590d\u6742\u60c5\u51b5<\/h2>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u590d\u6742\u60c5\u51b5\uff0c\u4f8b\u5982PDF\u94fe\u63a5\u7684URL\u4e0d\u662f\u7edd\u5bf9\u8def\u5f84\u3001PDF\u5185\u5bb9\u9700\u8981\u8fdb\u4e00\u6b65\u5904\u7406\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5904\u7406\u8fd9\u4e9b\u60c5\u51b5\u7684\u5efa\u8bae\uff1a<\/p>\n<\/p>\n
1\u3001\u5904\u7406\u76f8\u5bf9\u8def\u5f84\u7684PDF\u94fe\u63a5<\/h3>\n<\/p>\n
\u6709\u4e9b\u7f51\u9875\u4e2d\u7684PDF\u94fe\u63a5\u53ef\u80fd\u662f\u76f8\u5bf9\u8def\u5f84\uff0c\u9700\u8981\u5c06\u5176\u8f6c\u6362\u4e3a\u7edd\u5bf9\u8def\u5f84\u3002<\/p>\n<\/p>\n
from urllib.parse import urljoin<\/p>\n
def get_pdf_links(url):<\/p>\n
    response = requests.get(url)<\/p>\n
    soup = BeautifulSoup(response.content, 'html.parser')<\/p>\n
    pdf_links = []<\/p>\n
    for link in soup.find_all('a', href=True):<\/p>\n
        href = link['href']<\/p>\n
        if href.endswith('.pdf'):<\/p>\n
            pdf_links.append(urljoin(url, href))<\/p>\n
    return pdf_links<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5904\u7406PDF\u5185\u5bb9<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u67d0\u4e9bPDF\u6587\u4ef6\uff0cPyPDF2<\/code>\u5e93\u53ef\u80fd\u65e0\u6cd5\u6b63\u786e\u63d0\u53d6\u6587\u672c\u5185\u5bb9\u3002\u53ef\u4ee5\u5c1d\u8bd5\u4f7f\u7528\u5176\u4ed6\u5e93\uff08\u5982pdfminer<\/code>\uff09\u6765\u5904\u7406\u8fd9\u4e9b\u6587\u4ef6\u3002<\/p>\n<\/p>\n
pip install pdfminer.six<\/p>\n
<\/code><\/pre>\n<\/p>\n
from pdfminer.high_level import extract_text<\/p>\n
def read_pdf_with_pdfminer(file_path):<\/p>\n
    content = extract_text(file_path)<\/p>\n
    return content<\/p>\n
pdf_content = read_pdf_with_pdfminer(pdf_file_path)<\/p>\n
print(pdf_content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u60a8\u5e94\u8be5\u80fd\u591f\u4f7f\u7528Python\u722c\u53d6PDF\u6587\u4ef6\u5e76\u8bfb\u53d6\u5176\u5185\u5bb9\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\u6765\u5904\u7406\u590d\u6742\u60c5\u51b5\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u83b7\u53d6PDF\u6587\u6863\u7684\u5185\u5bb9\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u4e2a\u5e93\u6765\u63d0\u53d6PDF\u6587\u6863\u7684\u5185\u5bb9\uff0c\u5982PyPDF2\u3001pdfplumber\u548cPyMuPDF\u7b49\u3002\u901a\u8fc7\u8fd9\u4e9b\u5e93\uff0c\u4f60\u53ef\u4ee5\u8bfb\u53d6PDF\u6587\u4ef6\u7684\u6587\u672c\u3001\u63d0\u53d6\u56fe\u50cf\u548c\u5904\u7406PDF\u8868\u5355\u7b49\u3002\u5177\u4f53\u6b65\u9aa4\u5305\u62ec\u5b89\u88c5\u5e93\u3001\u6253\u5f00PDF\u6587\u4ef6\u5e76\u4f7f\u7528\u76f8\u5e94\u7684\u65b9\u6cd5\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/p>\n
\u4f7f\u7528Python\u722c\u53d6PDF\u6587\u4ef6\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u95ee\u9898\uff1f<\/strong>
\u5728\u722c\u53d6PDF\u6587\u4ef6\u65f6\uff0c\u9700\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684\u722c\u866b\u653f\u7b56\u548c\u7248\u6743\u6cd5\u3002\u5f88\u591a\u7f51\u7ad9\u5728robots.txt\u6587\u4ef6\u4e2d\u4f1a\u89c4\u5b9a\u54ea\u4e9b\u5185\u5bb9\u53ef\u4ee5\u88ab\u722c\u53d6\uff0c\u786e\u4fdd\u9075\u5b88\u8fd9\u4e9b\u89c4\u5b9a\u3002\u6b64\u5916\uff0c\u5904\u7406PDF\u6587\u4ef6\u7684\u683c\u5f0f\u548c\u7f16\u7801\u53ef\u80fd\u4f1a\u6709\u6240\u4e0d\u540c\uff0c\u56e0\u6b64\u5728\u63d0\u53d6\u6570\u636e\u65f6\u8981\u8003\u8651\u5230\u6587\u672c\u7684\u51c6\u786e\u6027\u548c\u5b8c\u6574\u6027\u3002<\/p>\n
\u722c\u866b\u8fc7\u7a0b\u4e2d\u5982\u4f55\u5904\u7406PDF\u6587\u4ef6\u7684\u4e0b\u8f7d\u548c\u4fdd\u5b58\uff1f<\/strong>
\u4f7f\u7528Python\u7684requests\u5e93\u53ef\u4ee5\u8f7b\u677e\u4e0b\u8f7dPDF\u6587\u4ef6\u3002\u4e0b\u8f7d\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528os\u6216shutil\u5e93\u5c06\u6587\u4ef6\u4fdd\u5b58\u5230\u6307\u5b9a\u7684\u76ee\u5f55\u3002\u786e\u4fdd\u5728\u4fdd\u5b58\u6587\u4ef6\u65f6\u4f7f\u7528\u5408\u9002\u7684\u6587\u4ef6\u540d\u548c\u6269\u5c55\u540d\uff0c\u4ee5\u4fbf\u540e\u7eed\u7684\u5904\u7406\u548c\u8bbf\u95ee\u3002\u901a\u8fc7\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u5934\uff0c\u53ef\u4ee5\u907f\u514d\u56e0\u53cd\u722c\u866b\u673a\u5236\u800c\u5bfc\u81f4\u7684\u4e0b\u8f7d\u5931\u8d25\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u722c\u53d6PDF\u6587\u6863\uff0c\u6709\u591a\u79cd\u65b9\u6cd5\u548c\u5de5\u5177\u53ef\u4ee5\u4f7f\u7528\uff0c\u5305\u62ecrequests\u5e93\u3001BeautifulSoup\u5e93 […]","protected":false},"author":3,"featured_media":1026603,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1026592"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1026592"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1026592\/revisions"}],"predecessor-version":[{"id":1026606,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1026592\/revisions\/1026606"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1026603"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1026592"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1026592"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1026592"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}