图片能离线下嘛 about yuque-crawl HOT 1 OPEN

import sys
import requests
import json
import re
import os
import urllib.parse

def get_image_filename(url):
    """从URL中提取简化后的图片文件名"""
    parsed_url = urllib.parse.urlparse(url)
    path = parsed_url.path
    filename = os.path.basename(path)
    return filename.split('#')[0]  # 分离出主文件名部分

def download_image(image_url, save_path):
    """下载图片并保存到指定路径"""
    try:
        response = requests.get(image_url)
        if response.status_code == 200:
            with open(save_path, 'wb') as file:
                file.write(response.content)
    except Exception as e:
        print(f"Error downloading image {image_url}: {e}")

def replace_image_links(markdown_content, book_id):
    """替换Markdown中的图片链接为本地链接，并下载图片"""
    image_links = re.findall(r'!\[.*?\]\((.*?)\)', markdown_content)
    for link in image_links:
        image_name = get_image_filename(link)
        download_path = f"download/{book_id}/images/{image_name}"
        download_image(link, download_path)
        markdown_content = markdown_content.replace(link, f"./images/{image_name}")
    return markdown_content

def save_page(book_id, slug, path):
    """保存页面为Markdown文件，下载并更新图片链接"""
    try:
        docsdata = requests.get(
            f'https://www.yuque.com/api/docs/{slug}?book_id={book_id}&merge_dynamic_data=false&mode=markdown')
        if docsdata.status_code != 200:
            print("Failed to download document. Page might be deleted.", book_id, slug)
            return
        docsjson = json.loads(docsdata.content)
        markdown_content = replace_image_links(docsjson['data']['sourcecode'], book_id)
        with open(path, 'w', encoding='utf-8') as file:
            file.write(markdown_content)
    except Exception as e:
        print(f"Error saving page: {e}")

def get_book(url="https://www.yuque.com/burpheart/phpaudit"):
    """获取书籍内容并保存为Markdown文件"""
    try:
        docsdata = requests.get(url)
        data = re.findall(r"decodeURIComponent\(\"(.+)\"\)\);", docsdata.content.decode('utf-8'))
        docsjson = json.loads(urllib.parse.unquote(data[0]))

        book_id = str(docsjson['book']['id'])
        image_dir = f"download/{book_id}/images"
        if not os.path.exists(image_dir):
            os.makedirs(image_dir)

        for doc in docsjson['book']['toc']:
            if doc['url']:
                filename = doc['title'].translate(str.maketrans('\/:*?"<>|\n\r', "___________")) + '.md'
                path = f"download/{book_id}/{filename}"
                save_page(book_id, doc['url'], path)
    except Exception as e:
        print(f"Error getting book: {e}")

if __name__ == '__main__':
    if len(sys.argv) > 1:
        get_book(sys.argv[1])
    else:
        get_book()