import requests from guanjianzi import keylist as keys import re from conMySql import ConDb from multiprocessing.dummy import Pool as ThreadPool s=requests.Session() con=ConDb() def getlist(url): html=s.get(url).content.decode() res=r'<li class="li"><font class="date">(.*?)</font><a href="(.*?)" target="_blank">(.*?)</a><span class="new"></span></li>' li=re.findall(res,html) title=re.findall(r"<title>(.*?)</title>",html)[0] for x,y,z in li: y=url+str(y) y=re.sub(r"\/index\.html\.",'',y) html1=s.get(y).content.decode() text=str(html1) guanjianzi = {} num = 0 for key in keys: # 循环遍历关键字列表,查询关键字出现的次数 count = text.count(key) # count 关键字在本文中出现的次数 if count > 0: guanjianzi.update({key: count}) # 把关键字和出现的次数添加到字典中 num += count print(title,y,z,guanjianzi,num,x) sql=''' insert into urllist(source,urls,titles,keyname,keysum,date1) values('{}','{}','{}',"{}",'{}','{}') '''.format(title,y,z,guanjianzi,num,x) con.runSql(sql) if __name__ == '__main__': urls = ['http://www.ndrc.gov.cn/xwzx/xwfb/index.html','http://www.ndrc.gov.cn/zwfwzx/zxgg/index.htmm','http://www.ndrc.gov.cn/zwfwzx/xzxknew/index.html','http://www.ndrc.gov.cn/zcfb/zcfbl/index.html','http://www.ndrc.gov.cn/zcfb/gfxwj/index.html','http://www.ndrc.gov.cn/zcfb/zcfbgg/index.html','http://www.ndrc.gov.cn/zcfb/zcfbghwb/index.html','http://www.ndrc.gov.cn/zcfb/zcfbtz/index.html','http://www.ndrc.gov.cn/zcfb/jd/index.html','http://www.ndrc.gov.cn/yjzq/index.html'] t=ThreadPool(5) for url in urls: t.apply_async(getlist,args=(url,)) t.close() t.join() sql1='select max(bat) from urllist limit 1' bat=con.runSql(sql1)[0][0] bat=int(bat)+1 # print(bat) sql2="update urllist set bat='{}'".format(bat) con.runSql(sql2)
python 线程池 分配任务给线程,爬取加入库。
猜你喜欢
转载自blog.csdn.net/u012593871/article/details/79045451
今日推荐
周排行