Python与SEO，三大SEO网站查询工具关键词查询采集源码！

# 5118网站关键词采集
# -*- coding: utf-8 -*-
import requests
from lxml import etree
import time
import logging

logging.basicConfig(filename='s5118.log', level=logging.DEBUG,format='%(asctime)s - %(levelname)s - %(message)s')

#获取关键词
def get_keywords(site,page):
    url="https://www.5118.com/seo/baidupc"
    headers={
        "Cookie":Cookie,
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
    }
    data={
        "isPager": "true",
        "viewtype": 2,
        "days": 90,
        "url": site,
        "orderField": "Rank",
        "orderDirection" : "sc",
        "pageIndex": page,
        "catalogName": "",
        "referKeyword": "",
    }
    response=requests.post(url=url,data=data,headers=headers,timeout=10)
    print(response.status_code)
    html=response.content.decode('utf-8')
    tree=etree.HTML(html)
    keywords=tree.xpath('//td[@class="list-col justify-content "]/a[@class="w100 all_array"]/text()')
    print(keywords)
    save_txt(keywords, site)
    return keywords


#存储为csv文件
def save_csv(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'5118_{filename}.csv','a+',encoding='utf-8-sig') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")


#存储为txt文件
def save_txt(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'5118_{filename}.txt','a+',encoding='utf-8') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")


def main(site):
    logging.info(f"开始爬取网站{site}关键词数据..")
    num = 100
    keys=[]
    for page in range(1,num+1):
        print(f"正在爬取第{page}页数据..")
        logging.info(f"正在爬取第{page}页数据..")
        try:
            keywords = get_keywords(site, page)
            keys.extend(keywords)
            time.sleep(8)
        except Exception as e:
            print(f"爬取第{page}页数据失败--错误代码：{e}")
            logging.error(f"爬取第{page}页数据失败--错误代码：{e}")
            time.sleep(10)

    keys = set(keys)  #去重
    save_csv(keys, site)


if __name__ == '__main__':
    site=""
    main(site)

# 爱站网站关键词采集
# -*- coding: utf-8 -*-
import requests
from lxml import etree
import time
import logging

logging.basicConfig(filename='aizhan.log', level=logging.DEBUG,format='%(asctime)s - %(levelname)s - %(message)s')

#获取关键词
def get_keywords(site,page):
    url=f"https://baidurank.aizhan.com/baidu/{site}/-1/0/{page}/position/1/"
    headers = {
        "Cookie":Cookie ,
    }
    response = requests.get(url=url,headers=headers, timeout=10)
    print(response.status_code)
    html = response.content.decode('utf-8')
    tree = etree.HTML(html)
    keywords = tree.xpath('//td[@class="title"]/a[@class="gray"]/@title')
    print(keywords)
    save_txt(keywords, site)
    return keywords


#存储为csv文件
def save_csv(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'aizhan_{filename}.csv','a+',encoding='utf-8-sig') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")


#存储为txt文件
def save_txt(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'aizhan_{filename}.txt','a+',encoding='utf-8') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")


def main(site):
    logging.info(f"开始爬取网站{site}关键词数据..")
    num = 50
    keys=[]
    for page in range(1,num+1):
        print(f"正在爬取第{page}页数据..")
        logging.info(f"正在爬取第{page}页数据..")
        try:
            keywords = get_keywords(site, page)
            keys.extend(keywords)
            time.sleep(8)
        except Exception as e:
            print(f"爬取第{page}页数据失败--错误代码：{e}")
            logging.error(f"爬取第{page}页数据失败--错误代码：{e}")
            time.sleep(10)

    keys = set(keys)  #去重
    save_csv(keys, site)


if __name__ == '__main__':
    site=""
    main(site)
    

# 站长之家网站关键词采集
# -*- coding: utf-8 -*-
import requests
from lxml import etree
import time
import logging

logging.basicConfig(filename='chinaz.log', level=logging.DEBUG,format='%(asctime)s - %(levelname)s - %(message)s')


#获取关键词
def get_keywords(site,page):
    headers={
        "Cookie":Cookie,
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
    }
    url=f"https://rank.chinaz.com/{site}-0---0-{page}"
    response=requests.get(url=url,headers=headers,timeout=8)
    print(response)
    html=response.content.decode('utf-8')
    tree=etree.HTML(html)
    keywords=tree.xpath('//ul[@class="_chinaz-rank-new5b"]/li[@class="w230 "]/a/text()')
    print(keywords)
    save_txt(keywords, site)
    return keywords


#存储为csv文件
def save_csv(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'chinaz_{filename}.csv','a+',encoding='utf-8-sig') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")

#存储为txt文件
def save_txt(keywords,site):
    filename=site.replace("www.",'').replace(".com",'').replace(".cn",'').replace('https://','').replace('http://','')
    for keyword in keywords:
        with open(f'chinaz_{filename}.txt','a+',encoding='utf-8') as f:
            f.write(f'{keyword}\n')
    print("保存关键词列表成功！")

def main(site):
    logging.info(f"开始爬取网站{site}关键词数据..")
    num = 50
    keys=[]
    for page in range(1,num+1):
        print(f"正在爬取第{page}页数据..")
        logging.info(f"正在爬取第{page}页数据..")
        try:
            keywords = get_keywords(site, page)
            keys.extend(keywords)
            time.sleep(8)
        except Exception as e:
            print(f"爬取第{page}页数据失败--错误代码：{e}")
            logging.error(f"爬取第{page}页数据失败--错误代码：{e}")
            time.sleep(10)

    keys = set(keys)  #去重
    save_csv(keys, site)


if __name__ == '__main__':
    site=""
    main(site)