naruto hentai manga

e-hentai爬⾍（更新）

使⽤了BeautifulSoup，re和urllib模块

#!/usr/bin/envpython

#-*-coding:utf-8-*-

__author__='Orange'

fromurllibimportrequest,par

importre

frombs4importBeautifulSoup

classItem(object):

time=''

img_url=''

tittle=''

down=''

def__init__(lf,time,img_url,tittle,down)->None:

=time

_url=img_url

=tittle

=down

defgetPages(html):

l(r'onclick="returnfal">(d+)',html)

defget_url(pages,key):

data={

'page':pages,

'f_doujinshi':'on',

'f_manga':'on',

'f_artistcg':'on',

'f_gamecg':'on',

'f_western':'on',

'f_non-h':'on',

'f_imaget':'on',

'f_cosplay':'on',

'f_asianporn':'on',

'f_misc':'on',

'f_arch':key,

'f_apply':'ApplyFilter'

}

url_parame=ode(data)

url="/?"

url_all=url+url_parame

returnurl_all

defgethtml(url):

req=t(url)

_header('Ur-Agent','Mozilla/5.0(Macintosh;IntelMacOSX10_12_5)AppleWebKit/537.36(KHTML,likeGecko)Chrome/59.0.3071.115Safari/537.36')

n(req)asf:

html=().decode('utf-8')

returnhtml

defgetDown(url):

html=gethtml(url)

soup=BeautifulSoup(html,'')

_all(href=e(r'/get/'))[0]['href']

defgetItems(html):

soup=BeautifulSoup(html,'')

_all('tr',class_=['gtr0','gtr1']):

time=_all('td',{'style':"white-space:nowrap"})[0].string

content=_all(class_='it2')[0].string

ifnotcontent:

img_url=_all('img')[1]['src']

tittle=_all('img')[1]['alt']

el:

mix=(r'~',content)

img_url='/'+mix[2]

tittle=mix[3]

_all(href=e(r'/')):

down=getDown(_all(href=e(r'/'))[0]['href'])

el:

down='em'

item=Item(time,img_url,tittle,down)

print(time,img_url,tittle,down)

returnitem

definit(key):

url=get_url(0,key)

html=gethtml(url)

pages=getPages(html)[-2]

items=[]

foriinrange(1,int(pages)):

url=get_url(i,key)

html=gethtml(url)

(getItems(html))

print(items)

if__name__=="__main__":

#key=input('输⼊搜索关键字(english):')

key='chine'

init(key)

可爬取图⽚，标题，时间，bt下载连接

⽆编写代理池,防爬⾍功能

**(后续更新)**

增加了bt转磁⼒链接,可直接对接到mysql存储,代码之后贴出来