联系方式丰富技能

三层联系方式提取。优先运行最便宜的方法，仅在必要时升级。

提取层级

第一层：直接HTML抓取（免费，始终优先尝试）
→ 检查：首页、/contact、/about、/about-us、/contact-us
→ 提取：所有邮箱、所有电话号码、企业名称
↓ （如果未找到邮箱）
第二层：WHOIS查询（免费）
→ 提取：注册组织、注册邮箱
↓ （如果仍未找到邮箱）
第三层：Hunter.io API（付费，每月25次免费）
→ 域名搜索 → 已验证邮箱 + 名/姓 + 职位

输出格式

python
{
business_name: Green Valley Landscaping,
emails: [info@greenvalley.com, john@greenvalley.com],
primary_email: info@greenvalley.com,
phones: [(503) 555-0123],
primary_phone: (503) 555-0123,
owner_name: John Smith, # 来自Hunter.io或关于页面
whois_org: Green Valley LLC,
whois_email: registrant@email.com,
source: scrape, # scrape | whois | hunter
confidence: high # high | medium | low
}

第一层：直接HTML抓取

python
import re, requests
from bs4 import BeautifulSoup

HEADERS = {
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36
}

EMAIL_REGEX = re.compile(
r\b[a-zA-Z0-9._%+\-]+@[a-zA-Z0-9.\-]+\.[a-zA-Z]{2,}\b
)

PHONE_REGEX = re.compile(
r(\+?1[-.\s]?)?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}
)

绝不可能是真实联系方式的邮箱

def isvalidemail(email: str) -> bool:
domain = email.split(@)[-1].lower()
return domain not in EMAIL_BLACKLIST and len(email) < 100

def scrape_page(url: str) -> tuple[str, str]:
获取页面。返回(html, final_url)。
try:
r = requests.get(url, headers=HEADERS, timeout=8, allow_redirects=True)
if r.status_code < 400:
return r.text, r.url
except Exception:
pass
return , url

def extractfromhtml(html: str) -> dict:
soup = BeautifulSoup(html, lxml)
text = soup.get_text(separator= )

# 提取邮箱
emails = list({e for e in EMAILREGEX.findall(text) if isvalid_email(e)})

# 提取电话
phonesraw = PHONEREGEX.findall(text)
phones = list({p[0] + p[1] if isinstance(p, tuple) else p for p in phones_raw})
# 清理：移除过短的匹配项
phones = [p.strip() for p in phones if len(re.sub(r\D, , p)) >= 10]

# 从标题提取企业名称
title = soup.find(title)
business_name =
if title:
t = title.text.strip()
# 取第一个有意义的片段
for sep in [|, –, -, ·, —, :]:
if sep in t:
t = t.split(sep)[0].strip()
break
business_name = t

return {emails: emails, phones: phones, businessname: businessname}

def scrapecontactpages(baseurl: str, existinghtml: str = ) -> dict:

抓取多个页面以获取联系信息。
existing_html：传入已由website-auditor获取的HTML，避免重复获取。

from urllib.parse import urljoin

all_emails = set()
all_phones = set()
business_name =

# 先尝试首页（如果已有HTML则使用）
if existing_html:
data = extractfromhtml(existing_html)
all_emails.update(data[emails])
all_phones.update(data[phones])
businessname = data[businessname]

# 尝试联系/关于页面
contact_paths = [/contact, /about, /contact-us, /about-us,
/get-in-touch, /reach-us, /find-us]

for path in contact_paths:
if all_emails:
break # 已找到邮箱——无需继续爬取
url = urljoin(base_url, path)
html, = scrapepage(url)
if html:
data = extractfromhtml(html)
all_emails.update(data[emails])
all_phones.update(data[phones])
if not business_name:
businessname = data[businessname]

emails = list(all_emails)
phones = list(all_phones)

return {
emails: emails,
primary_email: emails[0] if emails else None,
phones: phones,
primary_phone: phones[0] if phones else None,
businessname: businessname,
source: scrape,
confidence: high if emails else low
}

第二层：WHOIS查询

python
import whois # pip install python-whois

def whois_lookup(domain: str) -> dict:

查询WHOIS注册数据。
如果公开可用，返回注册组织+邮箱。

try:
w = whois.whois(domain)

# 提取邮箱（部分注册商隐藏了这些信息）
emails = w.emails if isinstance(w.emails, list) else ([w.emails] if w.emails else [])
emails = [e for e in emails if e and isvalidemail(e) and whoisprotect not in e.lower()
and privacy not in e.lower() and proxy not in e.lower()]

org = w.get(org) or w.get(registrant_organization) or
creation = w.get(creation_date)
if isinstance(creation, list):
creation = creation[0]

return {
whois_org: org,
whois_email: emails[0] if emails else None,
whois_emails: emails,
domain_created: str(creation)[:10] if creation else None,
registrar: w.get(registrar)
}
except Exception as e:
return {whoisorg: None, whoisemail: None, whois_error: str(e)}

第三层：Hunter.io API

python
import requests, os

def hunterdomainsearch(domain: str, limit: int = 5) -> dict:

在Hunter.io上搜索与域名关联的邮箱。
返回已验证的企业邮箱+联系人姓名。
需要设置HUNTERAPIKEY环境变量。
免费：每月25次搜索 | 入门版：每月34美元500次

apikey = os.environ.get(HUNTERAPI_KEY)
if not api_key:
return {hunteremails: [], huntersource: no_key}

params = {
domain: domain,
apikey: apikey,
limit: limit,
type: personal # personal | generic
}

try:
r = requests.get(https://api.hunter.io/v2/domain-search, params=params, timeout=10)
data = r.json().get(data, {})

contacts = []
for email_obj in data.get(emails, []):
contacts.append({
email: email_obj.get(value),
firstname: emailobj.get(first_name),
lastname: emailobj.get(last_name),
position: email_obj.get(position),
confidence: email_obj.get(confidence),
linkedin: email_obj.get(linkedin)
})

primary = contacts[0] if contacts else {}

return {
hunter_emails: [c[email] for c in contacts if c[email]],
primary_email: primary.get(email),
ownername: f{primary.get(firstname, )} {primary.get(last_name,