#python2.7?打造多線程網(wǎng)絡(luò)爬蟲
#庫:threading??安裝lxmlrequestsbs4（beautifulsoup?4）
#?-*-?coding:utf-8?-*-
import?requeststhreading#多線程
from?lxml?import?etree#解析方式
from?bs4?import?BeautifulSoup
#獲取源碼
def?get_html（url）:
	#url=‘https://www.doutula.com/article/list/?page=1‘
	headers={‘User-Agent‘:‘Mozilla/5.0?（Windows?NT?6.1;?WOW64）?AppleWebKit/537.36?（KHTML?like?Gecko）?Chrome/53.0.2785.104?Safari/537.36?Core/1.53.2595.400?QQBrowser/9.6.10872.400‘}
	request=requests.get（url=urlheaders=headers）
	response=request.content#獲取源碼
	#print?response
	return?response
#找到圖片的超鏈接獲取源碼
#獲取外頁??獲取超鏈接
def?get_img_html（html）:
	soup=BeautifulSoup（html‘lxml‘）#解析網(wǎng)頁方式自帶html.parser
	all_a=soup.find_all（‘a(chǎn)‘class_=‘list-group-item‘）#找到a標(biāo)簽
	for?i?in?all_a:#i是鏈接
		img_html=get_html（i[‘href‘]）#獲取超鏈接源碼
		g