1688商家实时采集软件 阿里巴巴卖家电话导出工具分享

pip install requests beautifulsoup4

python export_1688_phones.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"
    )
}

# 匹配手机号、常见座机号
PHONE_PATTERN = re.compile(
    r"(?:(?:\+?86)?1[3-9]\d{9}|0\d{2,3}[- ]?\d{7,8})"
)


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=10)
        if resp.status_code == 200:
            return resp.text
        print(f"请求失败，状态码：{resp.status_code}，URL：{url}")
    except Exception as e:
        print(f"请求异常：{e}，URL：{url}")
    return None


def extract_phones(html: str):
    """从公开 HTML 中提取电话"""
    soup = BeautifulSoup(html, "html.parser")
    text = soup.get_text(separator=" ", strip=True)

    phones = PHONE_PATTERN.findall(text)

    # 提取 tel: 链接中的电话
    for a in soup.find_all("a", href=True):
        href = a["href"].strip()
        if href.lower().startswith("tel:"):
            phones.append(href[4:].strip())

    cleaned = set()
    for phone in phones:
        phone = re.sub(r"[\s\-()]", "", phone)
        if phone.startswith("+86"):
            phone = phone[3:]
        if phone:
            cleaned.add(phone)

    return sorted(cleaned)


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", "商家电话"])
        writer.writerows(rows)


def main():
    # 请替换为公开且允许访问的页面 URL
    urls = [
        # "https://detail.1688.com/offer/xxxxxxxx.html",
    ]

    all_rows = []

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

        phones = extract_phones(html)
        for phone in phones:
            all_rows.append([url, phone])

        # 单线程限速，避免对平台造成压力
        time.sleep(5)

    export_csv(all_rows, "1688_public_phones.csv")
    print(f"导出完成，共 {len(all_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)
    phones = re.findall(r"(?:(?:\+?86)?1[3-9]\d{9}|0\d{2,3}[- ]?\d{7,8})", text)

    cleaned = set()
    for p in phones:
        p = re.sub(r"[\s\-()]", "", p)
        if p.startswith("+86"):
            p = p[3:]
        cleaned.add(p)
    return sorted(cleaned)

print(extract_from_local("public_page.html"))