python百度关键词相关搜索采集，链轮查询采集相关关键词工具exe

python百度关键词相关搜索采集，链轮查询采集相关关键词工具exe

1.随机生成协议头
2.关键词相关筛选
3.关键词去重
4.链轮采集

#百度关键词相关搜索采集
#20191118
# -*- coding: UTF-8 -*-

import requests,re,time
from fake_useragent import UserAgent
from bs4 import BeautifulSoup

#随机生成协议头
def ua():
    ua=UserAgent()
    headers = {"User-Agent": ua.random}
    return headers

#筛选词初始设定
req="工业|产品|外观|结构|造型|手机|犀牛|rhino|proe"


#筛选关键词
def search(req,con,n):
    text=re.search(req,con)
    if text:
        data=text.group(n)
    else:
        data='no'
    return data

#获取相关关键词源码
def get_a(key):
    response = requests.get(f"https://www.baidu.com/s?ie=utf-8&tn=baidu&wd={key}", headers=ua(), timeout=5).text
    time.sleep(2)
    soup = BeautifulSoup(response, 'lxml')
    div = soup.find('div', id='rs').find_all('a')
    return div


#相关关键词链轮查询采集
def get_keywords(keywords):
    xg_keywords=keywords

    all_keywords=[]
    for key in keywords:
        print(">>>开始查询 %s 相关关键词！" % key)
        try:
            div=get_a(key)
        except Exception as e:
            print(f'错误代码：{e}')
            print(f'正在重新获取网页内容...')
            time.sleep(5)
            div = get_a(key)

        for a in div:
            keyword=a.get_text()
            print(keyword)

            #筛选
            if search(r'(%s)'%req,keyword,1) =='no':
                print(f'-剔除关键词 {keyword}')
            else:
                print(f'>>获取关键词 {keyword}')

                print(xg_keywords)
                #去重
                if keyword not in xg_keywords:
                    xg_keywords.append(keyword)
                    all_keywords.append(keyword)

    #链轮
    get_keywords(all_keywords)


if __name__ == '__main__':
    get_keywords(["工业设计培训"])

代码参考来源：流量贩子 《seo应用编程》

版本二

百度相关搜索关键词抓取
1.读取txt文档关键词
2.导出txt关键词
3.多线程采集关键词

#百度相关搜索关键词抓取，读取txt关键词，导出txt关键词

# -*- coding=utf-8 -*-
import requests
import re
import time
from multiprocessing.dummy import Pool as ThreadPool


#百度相关关键词查询
def xgss(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"
    }
    html=requests.get(url,headers=headers).text
    #print(html)
    ze=r'<div id="rs"><div class="tt">相关搜索</div><table cellpadding="0">(.+?)</table></div>'
    xgss=re.findall(ze,html,re.S)
    #print(xgss)
    xgze=r'<th><a href="(.+?)">(.+?)</a></th>'
    sj=re.findall(xgze,str(xgss),re.S)
    #print(sj)
    gjc=''
    for x in sj:
        print(x[1])
        gjc=gjc+x[1]+'\n'

    # 导出关键词为txt文本
    with open(".\gjcsj.txt", 'a', encoding='utf-8') as f:
        f.write(gjc)
    print("-----------------------------------")
    return gjc


print("程序运行，正在导入关键词列表！！！")
print("-----------------------------------")
# 导入要搜索的关键词txt列表
urls = []
data = []
for line in open('.\gjc.txt', "r", encoding='utf-8'):
    data.append(line)
print("导入关键词列表成功！")
print("-----------------------------------")

#转换关键词为搜索链接
for keyword in data:
    url = 'https://www.baidu.com/s?wd=' + keyword
    urls.append(url)

print("采集百度相关搜索关键词开启！")
print("...................")
#多线程获取相关关键词
try:
    # 开4个 worker，没有参数时默认是 cpu 的核心数
    pool = ThreadPool()
    results = pool.map(xgss, urls)
    pool.close()
    pool.join()
    print("采集百度相关搜索关键词完成，已保存于gjcsj.txt！")
except:
    print("Error: unable to start thread")

print("8s后程序自动关闭！！！")
time.sleep(8)

exe下载地址：
链接: https://pan.baidu.com/s/1RhmZ99dYCSIJsEe-SnlhXQ
提取码: 9sjs