SEO自动化与Python工具：让重复工作高效运转
为什么SEO需要自动化？
重复性高的SEO任务：
- 每日排名检查（手动效率低）
- 批量检查页面状态码（网站越大越难手动）
- 监控竞品新发布内容
- 定期生成SEO报告
- 批量优化元数据（大规模网站）
自动化的价值：
- 节省70-80%的重复性工作时间
- 减少人为错误
- 实现实时监控（发现问题更快）
- 让SEO人员专注高价值分析工作
核心SEO自动化工具库
必备Python库
# 基础爬虫和请求
import requests
from bs4 import BeautifulSoup
# 数据分析
import pandas as pd
import numpy as np
# SEO专用
from googlesearch import search # Google搜索结果
import advertools # SEO数据分析
import serpapi # SERP数据API
# 可视化
import matplotlib.pyplot as plt
常用SEO自动化脚本
脚本1：批量页面状态检查
import requests
import pandas as pd
from urllib.parse import urlparse
def check_url_status(urls):
results = []
for url in urls:
try:
response = requests.get(url, timeout=10, allow_redirects=True)
final_url = response.url
status_code = response.status_code
results.append({
"original_url": url,
"final_url": final_url,
"status_code": status_code,
"redirected": url != final_url
})
except Exception as e:
results.append({
"original_url": url,
"final_url": None,
"status_code": None,
"error": str(e)
})
return pd.DataFrame(results)
# 使用
urls_to_check = ["https://example.com/page1", "https://example.com/page2"]
results_df = check_url_status(urls_to_check)
results_df.to_csv("url_status_report.csv", index=False)
print(f"检查完成：{len(results_df)}个URL")
脚本2：批量提取SEO元数据
import requests
from bs4 import BeautifulSoup
import pandas as pd
def extract_seo_metadata(url):
try:
response = requests.get(url, timeout=10)
soup = BeautifulSoup(response.content, "html.parser")
# 提取基础SEO数据
title = soup.find("title").text.strip() if soup.find("title") else ""
h1 = soup.find("h1").text.strip() if soup.find("h1") else ""
meta_desc = soup.find("meta", {"name": "description"})
description = meta_desc["content"] if meta_desc else ""
# 字数统计
body_text = soup.find("body").get_text() if soup.find("body") else ""
word_count = len(body_text.split())
# 内链统计
internal_links = [a["href"] for a in soup.find_all("a", href=True)
if urlparse(a["href"]).netloc == "" or
"yourdomain.com" in urlparse(a["href"]).netloc]
return {
"url": url,
"title": title,
"title_length": len(title),
"h1": h1,
"description": description,
"description_length": len(description),
"word_count": word_count,
"internal_link_count": len(internal_links)
}
except Exception as e:
return {"url": url, "error": str(e)}
# 从Sitemap批量提取
sitemap_urls = ["https://example.com/page1", ...]
metadata_df = pd.DataFrame([extract_seo_metadata(url) for url in sitemap_urls])
metadata_df.to_csv("seo_metadata_audit.csv", index=False)
脚本3：竞品内容监控
import feedparser
import hashlib
import json
from datetime import datetime
def monitor_competitor_content(rss_feeds):
"""监控竞品RSS订阅，发现新内容"""
new_content = []
# 加载已知内容哈希
try:
with open("known_content.json", "r") as f:
known_hashes = json.load(f)
except FileNotFoundError:
known_hashes = {}
for feed_url, competitor_name in rss_feeds.items():
feed = feedparser.parse(feed_url)
for entry in feed.entries:
content_hash = hashlib.md5(entry.link.encode()).hexdigest()
if content_hash not in known_hashes:
new_content.append({
"competitor": competitor_name,
"title": entry.title,
"url": entry.link,
"published": entry.published if hasattr(entry, "published") else ""
})
known_hashes[content_hash] = {
"url": entry.link,
"discovered_at": datetime.now().isoformat()
}
# 更新已知内容
with open("known_content.json", "w") as f:
json.dump(known_hashes, f, ensure_ascii=False)
return new_content
# 使用示例
rss_feeds = {
"https://competitor1.com/feed": "竞品A",
"https://competitor2.com/rss.xml": "竞品B"
}
new_articles = monitor_competitor_content(rss_feeds)
if new_articles:
print(f"发现{len(new_articles)}篇竞品新内容！")
脚本4：自动Sitemap更新
import xml.etree.ElementTree as ET
from datetime import datetime
def update_sitemap(sitemap_path, new_urls):
"""向Sitemap添加新URL"""
tree = ET.parse(sitemap_path)
root = tree.getroot()
namespace = "http://www.sitemaps.org/schemas/sitemap/0.9"
ET.register_namespace("", namespace)
for url_data in new_urls:
url_element = ET.SubElement(root, f"{{{namespace}}}url")
loc = ET.SubElement(url_element, f"{{{namespace}}}loc")
loc.text = url_data["loc"]
lastmod = ET.SubElement(url_element, f"{{{namespace}}}lastmod")
lastmod.text = url_data.get("lastmod", datetime.now().strftime("%Y-%m-%d"))
priority = ET.SubElement(url_element, f"{{{namespace}}}priority")
priority.text = str(url_data.get("priority", 0.8))
tree.write(sitemap_path, encoding="UTF-8", xml_declaration=True)
print(f"Sitemap更新完成，添加了{len(new_urls)}个URL")
Google Search Console API自动化
使用GSC API自动提取数据，避免手动导出：
from googleapiclient.discovery import build
from oauth2client.service_account import ServiceAccountCredentials
import pandas as pd
def get_gsc_data(site_url, start_date, end_date, dimensions=["query", "page"]):
"""从GSC API提取搜索数据"""
scopes = ["https://www.googleapis.com/auth/webmasters.readonly"]
credentials = ServiceAccountCredentials.from_json_keyfile_name(
"service_account.json", scopes
)
service = build("searchconsole", "v1", credentials=credentials)
request = {
"startDate": start_date,
"endDate": end_date,
"dimensions": dimensions,
"rowLimit": 25000
}
response = service.searchanalytics().query(siteUrl=site_url, body=request).execute()
rows = response.get("rows", [])
data = [{
**{dim: row["keys"][i] for i, dim in enumerate(dimensions)},
"clicks": row["clicks"],
"impressions": row["impressions"],
"ctr": row["ctr"],
"position": row["position"]
} for row in rows]
return pd.DataFrame(data)
# 使用示例
df = get_gsc_data("https://yourdomain.com", "2026-04-27", "2026-05-27")
df.to_csv("gsc_data.csv", index=False)
总结
SEO自动化是提升团队效率的重要手段。以上脚本提供了最常用的SEO自动化起点。建议从批量状态检查和元数据提取开始，逐步建立完整的SEO自动化工作流。随着自动化水平提升，SEO团队可以将更多精力投入到策略思考和内容创作等高价值工作中。