import re
import os
import requests
import time
from urllib.parse import urlparse, unquote
import hashlib

# 请求网址
url = 'https://mp.weixin.qq.com/s/DWsowFDU7D5baNyTGXDWGw'

# 请求头（添加更多头部信息以提高成功率）
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    'referer': 'https://mp.weixin.qq.com/',
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
    'cache-control': 'max-age=0',
    'connection': 'keep-alive',
}

try:
    response = requests.get(url=url, headers=headers, timeout=30)
    response.raise_for_status()
    response.encoding = response.apparent_encoding
except Exception as e:
    print(f"请求失败: {e}")
    exit()

# 改进的正则表达式，更精确地匹配图片链接
# 匹配微信文章中的图片链接格式
patterns = [
    # 匹配微信图片链接（带wx_fmt参数）
    r'data-src="(https?://mmbiz\.qpic\.cn/[^"]+?wx_fmt=(?:jpeg|png|gif|bmp|webp)[^"]*?)"',
    r'src="(https?://mmbiz\.qpic\.cn/[^"]+?wx_fmt=(?:jpeg|png|gif|bmp|webp)[^"]*?)"',
    # 匹配其他常见的图片链接
    r'(https?://mmbiz\.qpic\.cn/[^"\s]+?\.(?:jpg|jpeg|png|gif|bmp|webp)[^\s"]*)',
]

all_image_urls = []
for pattern in patterns:
    matches = re.findall(pattern, response.text, re.IGNORECASE)
    all_image_urls.extend(matches)

# 过滤掉不需要的链接
def is_valid_image_url(url):
    """检查是否是有效的图片链接"""
    # 排除JS文件、GIF占位图等
    exclude_patterns = [
        'js',
        'pic_blank.gif',
        '//res.wx.qq.com/',
        '.concat',
        'hit_biz_headimg',
        'emoji_url',
    ]
    
    for pattern in exclude_patterns:
        if pattern in url:
            return False
    
    # 必须是有效的URL
    if not url.startswith(('http://', 'https://')):
        return False
    
    # 检查是否是图片格式
    img_extensions = ['.jpg', '.jpeg', '.png', '.gif', '.bmp', '.webp']
    for ext in img_extensions:
        if ext in url.lower():
            return True
    
    # 或者包含微信图片格式参数
    if 'wx_fmt=' in url.lower():
        return True
    
    return False

# 过滤和去重
valid_image_urls = []
for img_url in all_image_urls:
    if is_valid_image_url(img_url) and img_url not in valid_image_urls:
        valid_image_urls.append(img_url)

print(f"找到 {len(valid_image_urls)} 个有效图片链接:")
for i, img_url in enumerate(valid_image_urls, 1):
    print(f"{i:2d}. {img_url}")

# 指定保存路径
save_path = r"F:\测试\图片"

# 确保目录存在
if not os.path.exists(save_path):
    os.makedirs(save_path)
    print(f"创建目录: {save_path}")

# 下载图片
success_count = 0
fail_count = 0

for i, img_url in enumerate(valid_image_urls, 1):
    try:
        # 生成文件名
        # 从URL中提取有用的部分作为文件名
        parsed_url = urlparse(img_url)
        
        # 尝试获取图片格式
        fmt_match = re.search(r'wx_fmt=(\w+)', img_url, re.IGNORECASE)
        if fmt_match:
            ext = fmt_match.group(1).lower()
            if ext == 'jpeg':
                ext = 'jpg'
        else:
            # 从URL路径猜测扩展名
            path_lower = parsed_url.path.lower()
            if '.jpg' in path_lower or '.jpeg' in path_lower:
                ext = 'jpg'
            elif '.png' in path_lower:
                ext = 'png'
            elif '.gif' in path_lower:
                ext = 'gif'
            elif '.webp' in path_lower:
                ext = 'webp'
            else:
                ext = 'jpg'  # 默认
        
        # 使用序号和URL哈希作为文件名（避免特殊字符）
        url_hash = hashlib.md5(img_url.encode()).hexdigest()[:6]
        filename = f"weixin_image_{i:03d}_{url_hash}.{ext}"
        filepath = os.path.join(save_path, filename)
        
        # 如果文件已存在，跳过
        if os.path.exists(filepath):
            print(f"{i:2d}. 跳过: {filename} (已存在)")
            success_count += 1
            continue
        
        print(f"{i:2d}. 正在下载: {filename}")
        
        # 下载图片（添加图片请求特定的headers）
        img_headers = headers.copy()
        img_headers['accept'] = 'image/webp,image/apng,image/*,*/*;q=0.8'
        
        img_response = requests.get(img_url, headers=img_headers, timeout=30, stream=True)
        img_response.raise_for_status()
        
        # 检查是否是图片
        content_type = img_response.headers.get('Content-Type', '').lower()
        if 'image' not in content_type:
            print(f"    警告: 响应不是图片，类型: {content_type}")
        
        # 获取文件大小
        content_length = img_response.headers.get('Content-Length')
        if content_length:
            file_size = int(content_length)
        else:
            file_size = len(img_response.content)
        
        # 保存图片
        with open(filepath, 'wb') as f:
            if hasattr(img_response, 'iter_content'):
                # 使用流式下载
                for chunk in img_response.iter_content(chunk_size=8192):
                    if chunk:
                        f.write(chunk)
            else:
                f.write(img_response.content)
        
        # 验证文件大小
        actual_size = os.path.getsize(filepath)
        if file_size > 0 and actual_size < file_size * 0.9:  # 如果实际大小小于预期90%
            print(f"    警告: 文件可能未完整下载 (预期: {file_size}, 实际: {actual_size})")
        
        print(f"    保存成功: {filename} ({actual_size/1024:.1f} KB)")
        success_count += 1
        
        # 延迟，避免请求过快
        time.sleep(0.3)
        
    except requests.exceptions.RequestException as e:
        print(f"{i:2d}. 下载失败: {e}")
        fail_count += 1
    except Exception as e:
        print(f"{i:2d}. 处理失败: {e}")
        fail_count += 1

print(f"\n下载完成!")
print(f"成功: {success_count} 张")
print(f"失败: {fail_count} 张")
print(f"保存路径: {save_path}")

# 显示保存的文件
if success_count > 0:
    print("\n保存的文件:")
    img_files = [f for f in os.listdir(save_path) 
                 if f.lower().endswith(('.jpg', '.jpeg', '.png', '.gif', '.bmp', '.webp'))]
    
    for i, filename in enumerate(sorted(img_files)[:10], 1):  # 只显示前10个
        filepath = os.path.join(save_path, filename)
        size_kb = os.path.getsize(filepath) / 1024
        print(f"{i:2d}. {filename} ({size_kb:.1f} KB)")
    
    if len(img_files) > 10:
        print(f"... 还有 {len(img_files) - 10} 个文件")