本文共 1124 字，大约阅读时间需要 3 分钟。

话不多说，上代码：

class get_article_content(object):#对象属性只有传入的是初始值和末位置	"""抓取文章内容类""".............................省略	def run(initial_value, last_value):		article_urls = get_article_content.read_csv()#读取原始url		datas = get_article_content.crawl_article(article_urls, initial_value, last_value)#数据抓取		get_article_content.save_keyword_retrieval(datas)#数据保存class thread_crawl(object):	"""线程类"""	def __init__(self):		pass	def five_threads():		#抓取文章内容并进行检索关键词保存，5个线程		all_article_num = len([i for i in get_article_content.read_csv()])		tem = all_article_num // 5		t1 = threading.Thread(target=get_article_content.run,args=[0, tem])		t2 = threading.Thread(target=get_article_content.run,args=[tem, tem*2])		t3 = threading.Thread(target=get_article_content.run,args=[tem*2, tem*3])		t4 = threading.Thread(target=get_article_content.run,args=[tem*3, tem*4])		t5 = threading.Thread(target=get_article_content.run,args=[tem*4, all_article_num])		t1.start()		t2.start()		t3.start()		t4.start()		t5.start()		while 1:#如果线程都结束，就排序			if threading.activeCount() - 1 == 0:				sort_article.sort_it('keyword_retrieval.csv')#文章排序				break			time.sleep(10)

转载地址：http://rfkrn.baihongyu.com/