【糗百成人版地址】Urllib2爬取糗事百科成人版妹子图（老司机第四弹）

#-*-代码： utf-8-*-

From urllib 2 import request、urlerror和urlopen

Import re、urllib和OS

Defget _ URL _ content (URL，retry _ times=2) :

Print 'Downloading: '，URL

tree :

Send_headers={

用户代理“:”Mozilla(windows nt 6.2；RV :16.0)eco/2010 01 01 Firefox；而且，

Accept' :' text/html、application/XHTML XML、application/XML；Q=0.9，*/*；Q=0.8 '，

Connection': 'keep-alive '

}

Req=request (URL，headers=send _ headers)

Html _ content=urlopen (req)。read()。decode ('gbk '，' ignore ')。encode ('utf-)

Except URLError、e:

Print e.reason

Html_content=None

列印' retry times : '，retry _ times

If retry_times 0:

If hasattr (e，' code') and 500=e.code 6003360

Get _ URL _ content (URL、retry _ times-1)

Return html_content

defget _ pic _ URL(html _ content):

Pic_reg='src='(http://。*？(png|jpg|gif)' '

Patten=re.com pile (pic _ reg、re.ignorecase)

Return (html_content)

Defsave _ pic _ urllib (save _ path，pic _ URL) :

save _ pic _ name=save _ path('/')[len('/')-1]

If not os。(save_pic_name):

Print save_pic_name

Urllib.urlretrieve (pic _ URL、save _ pic _ name)

Def mkdir(mkdir_path):

Path=mkdir_()

If not os。(path):

Os.makedirs(路径)

Return path

# print get _ URL _ content('；)。

If _ _ name _ _==' _ _ main _ _ ' :

save _ path=mkdir(' d : \ \ meizi \ \ ')

For index in range(1，755): #按ID攀登整个站点

src=' http://www . qiubaichengren . com/% s . html ' %(index)

URL _ content=get _ URL _ content(src)

If url_content:

son _ save _ path=mkdir(save _ path str(index)' \ \ ')

pic _ list=get _ pic _ URL(URL _ content)

for I in range(len(pic _ list)):

Pic_url=pic_list[i][0]

Save _ pic _ urllib (son _ save _ path，pic _ URL)

打印“页”“str(索引)”页，爬网完成。

撸叼屎,拿去撸吧！'