python 线程池爬取词典网历史人物词库

飞熊 • 2023年8月8日下午8:42 • Python • 阅读 336

'''
python 词典网历史人物词库 线程池 爬取
https://search.cidianwang.com/
待处理人名文件下载地址：https://jhc001.lanzouw.com/iYkEqwj0o9e
				 密码:b0dh
				 
注：数据输出格式并未处理，少量数据解析格式存在问题
	本文章仅供参考交流学习，如做其他用途，产生一切后果请自负。

'''

#coding=utf-8
#coding=gbk
from concurrent.futures import ThreadPoolExecutor
import requests,os,re,asyncio,time
import threadpool
from lxml import etree


def spider(name):

    cookies = {
        'cookies'换成自己的
    }

    headers = {
        'Connection': 'keep-alive',
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
        'sec-ch-ua': '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
        'sec-ch-ua-mobile': '?0',
        'Upgrade-Insecure-Requests': '1',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'Sec-Fetch-Site': 'same-site',
        'Sec-Fetch-Mode': 'navigate',
        'Sec-Fetch-User': '?1',
        'Sec-Fetch-Dest': 'document',
        'Referer': 'https://www.cidianwang.com/',
        'Accept-Language': 'zh-CN,zh;q=0.9',
    }

    params = (
        ('q', name),
        ('m', '12'),
        ('y', '0'),
    )

    response = requests.get('https://search.cidianwang.com/', headers=headers, params=params, cookies=cookies)

    response.encoding = 'utf8'
    lis=re.findall('"><h1><a href="(.*?)" class="s_link"',response.text)
    if lis != []:
        r_lis = lis[0]
        detail_page2(name, r_lis)
        print(name+' --> 搜索成功')
    else:
        print(name+' --> 搜索结果为空')

# 词典解析
def detail_page2(name,r_lis):
    response=requests.get(r_lis)
    response.encoding='utf8'
    # print(response.text)
    tree=etree.HTML(response.text)
    lis=tree.xpath('//div[@class="content"]/div[@id="left"]/div/p[2]//text()')
    if lis != []:
        detail=str(lis)
        save_data(name, detail)
    else:
        print('空')


# 保存数据
def save_data(name,detail):
    with open('../results/results1.txt', 'a', encoding='utf-8') as fp:
        result=name+'\t : '+detail+'\n'
        fp.write(str(result).replace(',','').replace("'",'').replace('[','').replace(']','').replace('\n\t',''))




if __name__ == '__main__':
    os.makedirs('../results', exist_ok=True)
    try:
        with open('word1.txt', 'r', encoding='utf-8') as fp:
            words = fp.readlines()
            # 线程池 
            with ThreadPoolExecutor(50) as executor1:
                executor1.map(spider,words)
    except:
        x = input('执行异常！！！')