Python多线程采集百度相关搜索关键词

百度相关搜索关键词抓取，读取txt关键词，导出txt关键词

#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 >(.+?)</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)