Python脚本实现批量导出网站指定文章

目录

• 一 导出全部已发布文章
• 二 导出指定日期后的文章

首先，需要在本地安装3.8版本以上的python，安装python步骤

检查是否安装成功

pip3 --version

安装后执行

pip3 install requests beautifulsoup4 markdownify

新建脚本，脚本名字随意，这里是：csdn_downloader.py

脚本内容如下：

# -*- coding: utf-8 -*-
import os
import re
import requests
import time
from bs4 import BeautifulSoup
from markdownify import markdownify as md
from urllib.parse import urlparse, unquote
import hashlib
from pathlib import Path

# ================== 配置区 ==================
CSDN_USERNAME = "qq_33417321"  # ←←← 修改为你想下载的用户名
SAVE_DIR = Path("csdn_articles")  # 文章保存根目录（自动跨平台）
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36",
    "Referer": "https://blog.csdn.net/"
}

def sanitize_filename(name: str) -> str:
    """清理文件名，移除 Windows 非法字符和‘原创'字样"""
    name = name.replace("原创", "").strip()
    # 移除 Windows 非法字符
    name = re.sub(r'[\/*?:"<>|rn]', "_", name)
    return name or "untitled"

def get_article_list(username):
    """获取博主文章列表（标题和URL）"""
    url = f"https://blog.csdn.net/{username}/article/list"
    articles = []
    page = 1
    while True:
        response = requests.get(f"{url}/{page}", headers=HEADERS)
        soup = BeautifulSoup(response.text, 'html.parser')
        items = soup.select(".article-list .article-item-box")
        if not items:
            break
        for item in items:
            title_elem = item.select_one("h4 a")
            if not title_elem:
                continue
            title = title_elem.text.strip()
            link = title_elem["href"]
            articles.append({"title": title, "url": link})
        page += 1
        time.sleep(1)
    return articles

def download_image(img_url, save_path: Path):
    """下载单张图片到本地"""
    try:
        img_headers = HEADERS.copy()
        img_headers["Accept"] = "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8"
        response = requests.get(img_url, headers=img_headers, stream=True, timeout=30)
        if response.status_code == 200:
            save_path.parent.mkdir(parents=True, exist_ok=True)
            with open(save_path, 'wb') as f:
                for chunk in response.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
            return True
        else:
            print(f"图片下载失败（状态码：{response.status_code}）：{img_url}")
            return False
    except Exception as e:
        print(f"图片下载异常：{img_url}，错误：{str(e)}")
        return False

def get_image_extension(img_url):
    """从URL中获取图片扩展名"""
    parsed_url = urlparse(img_url)
    path = parsed_url.path.lower()
    extensions = ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.bmp', '.svg']
    for ext in extensions:
        if ext in path:
            return ext
    return '.jpg'

def process_images_in_content(content, article_title):
    """处理内容中的图片，下载并替换为本地路径"""
    soup = BeautifulSoup(content, 'html.parser')
    img_tags = soup.find_all('img')
    if not img_tags:
        return content

    # 清理文章标题用于路径
    safe_title = sanitize_filename(article_title)

    global_image_dir = SAVE_DIR / "images"
    article_image_dir = global_image_dir / safe_title

    for img in img_tags:
        img_url = img.get('src', '')
        if not img_url:
            continue

        # 处理协议相对路径
        if img_url.startswith('//'):
            img_url = 'https:' + img_url
        elif not img_url.startswith(('http://', 'https://')):
            continue  # 跳过无法处理的相对路径

        try:
            img_hash = hashlib.md5(img_url.encode()).hexdigest()[:8]
            img_ext = get_image_extension(img_url)
            img_filename = f"{img_hash}{img_ext}"

            local_img_path = article_image_dir / img_filename
            # Markdown 中使用正斜杠（/），兼容所有平台
            md_img_path = f"./images/{safe_title}/{img_filename}"

            if not local_img_path.exists():
                print(f"  下载图片：{img_filename}")
                if download_image(img_url, local_img_path):
                    img['src'] = md_img_path
                else:
                    print(f"  图片下载失败，保留原链接：{img_url}")
            else:
                img['src'] = md_img_path

        except Exception as e:
            print(f"  处理图片时出错：{img_url}，错误：{str(e)}")
            continue

    return str(soup)

def download_article(url, article_title):
    """下载单篇文章，处理图片后转为Markdown"""
    try:
        response = requests.get(url, headers=HEADERS, timeout=30)
        soup = BeautifulSoup(response.text, 'html.parser')
        content = soup.select_one("article")
        if not content:
            print(f"  未找到文章内容")
            return None

        processed_content = process_images_in_content(str(content), article_title)
        markdown_content = md(processed_content)
        return markdown_content
    except Exception as e:
        print(f"  下载文章时出错：{str(e)}")
        return None

def save_to_markdown(title, content, save_dir: Path):
    """保存Markdown文件"""
    save_dir.mkdir(parents=True, exist_ok=True)
    safe_title = sanitize_filename(title)
    filename = save_dir / f"{safe_title}.md"

    with open(filename, "w", encoding="utf-8") as f:
        f.write(f"# {title}nn")
        f.write(content)

    print(f"  已保存：{filename}")
    return filename

if __name__ == "__main__":
    print("开始获取文章列表...")
    articles = get_article_list(CSDN_USERNAME)
    print(f"找到 {len(articles)} 篇文章")

    success_count = 0
    fail_count = 0

    for i, article in enumerate(articles, 1):
        title = article["title"]
        url = article["url"]
        print(f"n[{i}/{len(articles)}] 处理文章：{title}")

        content = download_article(url, title)
        if content:
            save_to_markdown(title, content, SAVE_DIR)
            success_count += 1
        else:
            print(f"  文章下载失败：{title}")
            fail_count += 1

        time.sleep(2)

    print(f"n处理完成！成功：{success_count}篇，失败：{fail_count}篇")
    print(f"文章保存在：{SAVE_DIR.resolve()}")
    print("图片保存在：./images/ 目录下，Markdown文件可离线查看")

其中，脚本里CSDN_USERNAME的值，改为你要获取的csdn的用户名

获取用户名：点击作者头像后，链接里的这个值就是用户名（红框里的内容）

执行脚本

python csdn_downloader.py

执行日志入下：

由于要下载csdn文章里的图片，所以很慢，静静等待即可。下载过程中，会在脚本所在目录生成一个csdn_articles文件夹，里边是md文件以及存md里的图片的文件夹。

上边的脚本，一次性导出了所有已发布的文章，但是有时候我们的文章太多，每次备份不需要全部导出，只导出指定时间以后的文章，那么使用如下脚本即可，如脚本名为new.py，内容如下

# -*- coding: utf-8 -*-
import os
import re
import requests
import time
from bs4 import BeautifulSoup
from markdownify import markdownify as md
from urllib.parse import urlparse, unquote
import hashlib
from pathlib import Path
from datetime import datetime

# ================== 配置区 ==================
CSDN_USERNAME = "qq_33417321"  # ←←← 修改为你想下载的用户名
SAVE_DIR = Path("csdn_articles")  # 文章保存根目录（自动跨平台）

# ⬇️ 新增：设置最小发布日期（含）
MIN_PUBLISH_DATE = datetime(2026, 2, 7)  # 只下载 2026年2月1日及之后的文章

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36",
    "Referer": "https://blog.csdn.net/"
}

def sanitize_filename(name: str) -> str:
    """清理文件名，移除 Windows 非法字符和‘原创'字样"""
    name = name.replace("原创", "").strip()
    name = re.sub(r'[\/*?:"<>|rn]', "_", name)
    return name or "untitled"

def parse_publish_date(date_str: str) -> datetime | None:
    """尝试解析 CSDN 日期字符串，支持 '2025-06-15 10:30:00' 或 '2025-06-15' 等"""
    date_str = date_str.strip()
    for fmt in [
        "%Y-%m-%d %H:%M:%S",  # 带秒，如 2025-06-15 10:30:09
        "%Y-%m-%d %H:%M",     # 不带秒，如 2025-06-15 10:30
        "%Y-%m-%d"            # 只有日期，如 2025-06-15
    ]:
        try:
            return datetime.strptime(date_str, fmt)
        except ValueError:
            continue
    print(f"  无法解析日期：{date_str}")
    return None

def get_article_list(username, min_date=None):
    """获取博主文章列表（标题、URL、发布时间），可选按 min_date 过滤"""
    url = f"https://blog.csdn.net/{username}/article/list"
    articles = []
    page = 1
    early_stop = False

    while not early_stop:
        print(f"  正在抓取第 {page} 页...")
        response = requests.get(f"{url}/{page}", headers=HEADERS)
        soup = BeautifulSoup(response.text, 'html.parser')
        items = soup.select(".article-list .article-item-box")

        if not items:
            break

        current_page_has_valid = False  # 当前页是否有满足条件的文章

        for item in items:
            title_elem = item.select_one("h4 a")
            date_elem = item.select_one(".date")  # CSDN 通常用 .date 类表示发布时间

            if not title_elem:
                continue

            title = title_elem.text.strip()
            link = title_elem["href"]
            pub_date = None

            if date_elem:
                raw_date = date_elem.text.strip()
                pub_date = parse_publish_date(raw_date)

            # 如果设置了最小日期，且文章发布时间早于该日期，则跳过
            if min_date and pub_date and pub_date < min_date:
                continue

            # 如果发布时间未知但设置了 min_date，保守起见也跳过（或可选择保留）
            if min_date and not pub_date:
                print(f"  警告：无法获取文章 [{title}] 的发布时间，跳过（因设置了日期过滤）")
                continue

            articles.append({
                "title": title,
                "url": link,
                "publish_date": pub_date
            })
            current_page_has_valid = True

        # 如果当前页没有任何有效文章（全部早于 min_date），可提前终止
        if min_date and not current_page_has_valid and page > 1:
            print("  后续页面文章均早于指定日期，停止翻页。")
            early_stop = True

        page += 1
        time.sleep(1)

    return articles

# ========== 以下函数保持不变 ==========
def download_image(img_url, save_path: Path):
    try:
        img_headers = HEADERS.copy()
        img_headers["Accept"] = "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8"
        response = requests.get(img_url, headers=img_headers, stream=True, timeout=30)
        if response.status_code == 200:
            save_path.parent.mkdir(parents=True, exist_ok=True)
            with open(save_path, 'wb') as f:
                for chunk in response.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
            return True
        else:
            print(f"图片下载失败（状态码：{response.status_code}）：{img_url}")
            return False
    except Exception as e:
        print(f"图片下载异常：{img_url}，错误：{str(e)}")
        return False

def get_image_extension(img_url):
    parsed_url = urlparse(img_url)
    path = parsed_url.path.lower()
    extensions = ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.bmp', '.svg']
    for ext in extensions:
        if ext in path:
            return ext
    return '.jpg'

def process_images_in_content(content, article_title):
    soup = BeautifulSoup(content, 'html.parser')
    img_tags = soup.find_all('img')
    if not img_tags:
        return content

    safe_title = sanitize_filename(article_title)
    global_image_dir = SAVE_DIR / "images"
    article_image_dir = global_image_dir / safe_title

    for img in img_tags:
        img_url = img.get('src', '')
        if not img_url:
            continue
        if img_url.startswith('//'):
            img_url = 'https:' + img_url
        elif not img_url.startswith(('http://', 'https://')):
            continue

        try:
            img_hash = hashlib.md5(img_url.encode()).hexdigest()[:8]
            img_ext = get_image_extension(img_url)
            img_filename = f"{img_hash}{img_ext}"
            local_img_path = article_image_dir / img_filename
            md_img_path = f"./images/{safe_title}/{img_filename}"

            if not local_img_path.exists():
                print(f" 下载图片：{img_filename}")
                if download_image(img_url, local_img_path):
                    img['src'] = md_img_path
                else:
                    print(f" 图片下载失败，保留原链接：{img_url}")
            else:
                img['src'] = md_img_path
        except Exception as e:
            print(f" 处理图片时出错：{img_url}，错误：{str(e)}")
            continue

    return str(soup)

def download_article(url, article_title):
    try:
        response = requests.get(url, headers=HEADERS, timeout=30)
        soup = BeautifulSoup(response.text, 'html.parser')
        content = soup.select_one("article")
        if not content:
            print(f" 未找到文章内容")
            return None
        processed_content = process_images_in_content(str(content), article_title)
        markdown_content = md(processed_content)
        return markdown_content
    except Exception as e:
        print(f" 下载文章时出错：{str(e)}")
        return None

def save_to_markdown(title, content, save_dir: Path):
    save_dir.mkdir(parents=True, exist_ok=True)
    safe_title = sanitize_filename(title)
    filename = save_dir / f"{safe_title}.md"
    with open(filename, "w", encoding="utf-8") as f:
        f.write(f"# {title}nn")
        f.write(content)
    print(f" 已保存：{filename}")
    return filename

# ========== 主程序入口 ==========
if __name__ == "__main__":
    print("开始获取文章列表...")
    articles = get_article_list(CSDN_USERNAME, min_date=MIN_PUBLISH_DATE)
    print(f"找到 {len(articles)} 篇符合条件的文章（发布日期 ≥ {MIN_PUBLISH_DATE.strftime('%Y-%m-%d')}）")

    success_count = 0
    fail_count = 0

    for i, article in enumerate(articles, 1):
        title = article["title"]
        url = article["url"]
        pub_date = article.get("publish_date")
        date_str = pub_date.strftime("%Y-%m-%d") if pub_date else "未知"
        print(f"n[{i}/{len(articles)}] 处理文章：{title} （发布于 {date_str}）")

        content = download_article(url, title)
        if content:
            save_to_markdown(title, content, SAVE_DIR)
            success_count += 1
        else:
            print(f" 文章下载失败：{title}")
            fail_count += 1

        time.sleep(2)

    print(f"n处理完成！成功：{success_count}篇，失败：{fail_count}篇")
    print(f"文章保存在：{SAVE_DIR.resolve()}")
    print("图片保存在：./images/ 目录下，Markdown文件可离线查看")

记得修改MIN_PUBLISH_DATE 里的开始日期。之后执行脚本后，下载下来就是指定日期后的文章了。

到此这篇关于Python脚本实现批量导出网站指定文章的文章就介绍到这了,更多相关Python导出网站文章内容请搜索风君子博客以前的文章或继续浏览下面的相关文章希望大家以后多多支持风君子博客！

您可能感兴趣的文章:

• python如何导出微信公众号文章方法详解
• Python结合PyQt5实现目录文件扫描与导出工具
• Python实现获取手机通讯录文件并导出为excel
• Python实现将列表高效导出为 Excel 文件
• Python实现将列表导出为Excel文件
• 使用Python将Word文档导出为PDF格式并从Word文档中提取数据