阿里巴巴国际站商家实时导出软件使用教程分享

pip install requests beautifulsoup4

python export_alibaba_contacts.py

import csv
import re
import time
from urllib.parse import urlparse
from urllib.robotparser import RobotFileParser

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
        "AppleWebKit/537.36 (KHTML, like Gecko) "
        "Chrome/124.0.0.0 Safari/537.36"
    ),
    "Accept-Language": "en-US,en;q=0.9,zh-CN;q=0.8",
}

EMAIL_RE = re.compile(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}")
PHONE_RE = re.compile(r"\+?\d[\d\s\-()]{7,}\d")


def can_fetch(url: str) -> bool:
    """检查 robots.txt 是否允许抓取"""
    parsed = urlparse(url)
    robots_url = f"{parsed.scheme}://{parsed.netloc}/robots.txt"
    rp = RobotFileParser()
    rp.set_url(robots_url)
    try:
        rp.read()
    except Exception as e:
        print(f"读取 robots.txt 失败：{e}")
        return False
    return rp.can_fetch(HEADERS["User-Agent"], url)


def fetch_html(url: str):
    """获取公开页面 HTML，单线程、限速、超时"""
    if not can_fetch(url):
        print(f"robots.txt 不允许抓取：{url}")
        return None

    try:
        resp = requests.get(url, headers=HEADERS, timeout=15)
        resp.raise_for_status()
        return resp.text
    except Exception as e:
        print(f"请求异常：{e}，URL：{url}")
        return None


def clean_phone(phone: str) -> str:
    """简单清洗电话"""
    phone = re.sub(r"[\s\-()]", "", phone)
    if phone.startswith("00"):
        phone = "+" + phone[2:]
    return phone


def extract_contacts(html: str, url: str):
    """从公开 HTML 中提取公司名、邮箱、电话"""
    soup = BeautifulSoup(html, "html.parser")
    text = soup.get_text(separator=" ", strip=True)

    # 公司名 / 页面标题
    company = ""
    if soup.title:
        company = soup.title.get_text(strip=True)
    h1 = soup.find("h1")
    if h1:
        company = h1.get_text(" ", strip=True)

    emails = set(EMAIL_RE.findall(text))
    phones = set(PHONE_RE.findall(text))

    # 提取 mailto: 和 tel: 链接
    for a in soup.find_all("a", href=True):
        href = a["href"].strip()
        if href.lower().startswith("mailto:"):
            emails.add(href[7:].split("?")[0])
        if href.lower().startswith("tel:"):
            phones.add(href[4:])

    emails = {e.strip().lower() for e in emails if e.strip()}
    phones = {clean_phone(p) for p in phones if clean_phone(p)}

    return company, sorted(emails), sorted(phones)


def export_csv(rows, output_path: str):
    """导出 CSV"""
    with open(output_path, "w", newline="", encoding="utf-8-sig") as f:
        writer = csv.writer(f)
        writer.writerow(["来源URL", "公司/标题", "邮箱", "电话"])
        writer.writerows(rows)


def main():
    # 请替换为公开且允许访问的页面 URL
    urls = [
        # "https://www.alibaba.com/product-detail/xxxxxxxx.html",
    ]

    interval = 8  # 每次请求间隔，避免对平台造成压力
    rows = []

    for url in urls:
        print(f"正在处理：{url}")
        html = fetch_html(url)
        if not html:
            continue

        company, emails, phones = extract_contacts(html, url)

        if not emails and not phones:
            rows.append([url, company, "", ""])
        else:
            max_len = max(len(emails), len(phones), 1)
            for i in range(max_len):
                rows.append([
                    url,
                    company,
                    emails[i] if i < len(emails) else "",
                    phones[i] if i < len(phones) else "",
                ])

        time.sleep(interval)

    export_csv(rows, "alibaba_public_contacts.csv")
    print(f"导出完成，共 {len(rows)} 条记录。")


if __name__ == "__main__":
    main()

from bs4 import BeautifulSoup
import re

def extract_from_local(file_path):
    with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
        html = f.read()

    soup = BeautifulSoup(html, "html.parser")
    text = soup.get_text(" ", strip=True)

    emails = set(re.findall(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}", text))
    phones = set(re.findall(r"\+?\d[\d\s\-()]{7,}\d", text))

    return {
        "emails": sorted(emails),
        "phones": sorted({re.sub(r"[\s\-()]", "", p) for p in phones}),
    }

print(extract_from_local("public_page.html"))