发票形式是eml批量下载发票pdf

每一个eml文件打开就是这样的，包含一个发票链接：

1、提取提取eml文件中的发票链接

# 批量提取200个eml文件的链接地址，保存到发票链接.txt中，
import os
import re
import email
from email.policy import default

# ========== 配置 ==========
# 你的EML文件存放文件夹
EML_FOLDER = r"D:\XXXXX\合并完成_所有文件"
LINK_OUTPUT = r"D:\XXXXXX\发票链接.txt"
# ==================================================

# 正则匹配发票链接
pattern = re.compile(r"https://dppt\.hebei\.chinatax\.gov\.cn:8443/\S+")

def clean_url(url):
    """清理链接末尾多余符号"""
    url = url.split("'")[0]
    url = url.split('"')[0]
    url = url.split(">")[0]
    url = url.split("<")[0]
    url = url.strip()
    return url

def extract_from_one_eml(path):
    """单个EML提取链接，不去重，返回列表"""
    link_list = []
    try:
        with open(path, "rb") as f:
            msg = email.message_from_bytes(f.read(), policy=default)

        for part in msg.walk():
            if part.get_content_type() in ["text/plain", "text/html"]:
                try:
                    body = part.get_payload(decode=True).decode("utf-8", "ignore")
                except:
                    body = part.get_payload(decode=True).decode("gbk", "ignore")

                found = pattern.findall(body)
                for url in found:
                    clean_url_str = clean_url(url)
                    if clean_url_str:
                        link_list.append(clean_url_str)
    except Exception as e:
        print(f"⚠️ 解析异常：{os.path.basename(path)}，错误：{str(e)[:30]}")
    return link_list

def batch_extract():
    all_links = []
    files = [f for f in os.listdir(EML_FOLDER) if f.lower().endswith(".eml")]
    total_file = len(files)
    print(f"📂 共找到 {total_file} 个eml文件，开始提取...\n")

    for idx, fname in enumerate(files, 1):
        path = os.path.join(EML_FOLDER, fname)
        urls = extract_from_one_eml(path)
        # 追加到总列表，不去重
        all_links.extend(urls)
        print(f"[{idx}/{total_file}] {fname} → 提取 {len(urls)} 条链接")

    # 写入文件
    with open(LINK_OUTPUT, "w", encoding="utf-8") as f:
        for url in all_links:
            f.write(url + "\n")

    print(f"\n========================================")
    print(f"✅ 全部解析完成")
    print(f"📄 总文件数：{total_file}")
    print(f"🔗 总计提取链接：{len(all_links)} 条（未去重）")
    print(f"💾 链接已保存至：{LINK_OUTPUT}")

if __name__ == "__main__":
    batch_extract()

这样所有的链接都保存到发票链接.txt了，具体大致如下：一行就是一个链接

2、利用影刀软件设置自动化下载流程

我试了试爬虫会有反扒机制，不能批量下载发票pdf，试了试影刀这个软件，就可以下载。