python爬虫抓取分页_python爬虫 分页获取图片并下载

--刚接触python2天，想高速上手，就写了个爬虫，写完之后，成就感暴增，用起来顺手多了。

1.源代码

#coding=utf-8

import urllib

import re

class Page():

__slots__ = ('url', 'regex', 'arg' )

def __init__(this ,url ,regex ,arg ):

if not arg :

arg['download'] = False

arg['write'] = False

arg['outpath'] = ''

this.filter = Filter(url,{

'regex' : regex,

'custom' : arg['custom'] if arg.has_key('custom') else ''

})

this.url = url;

this.outpath = arg['outpath'] if arg.has_key('outpath') else ''

this.download =arg['download'] if arg.has_key('download') else False

this.write = arg['write'] if arg.has_key('write') else False

this.pagin = arg['pagin'] if arg.has_key('pagin') else False

def start(this ,*prefix):

_pagin = this.pagin; _getHtml = this.getHtml;_prefix = '1';

if len(prefix) >= 1 : _prefix = prefix[0];

_getHtml(this.url ,_prefix);

if _pagin != False :

_start = _pagin['start']; _end = _pagin['end']; _rule = _pagin['rule'];

while _start <= _end :

_getHtml(_rule.replace('{page}',str(_start)) ,str(_start));

_start += 1

def down(this ,url ,prefix):

try:

filename = str(prefix) + '_' + url[url.rfind("/")+1:]

urllib.urlretrieve(url, this.outpath + filename);

print 'download-succeed\t->',filename

except:

print 'download->failed'

def downs(this ,arr ,prefix):

for x in arr: this.down(x ,prefix);

def writeFile(this ,arr):

_file = open(this.outpath + 'list.txt', 'a+')

try:

_file.writelines('\n\n'+'\n'.join(arr))

finally:

_file.close()

def getHtml(this ,url ,prefix):

try:

_p = urllib.urlopen(url); html = _p.read(); _p.close()

html = unicode(html, "gb2312").encode("utf8")

arr = this.filter.execute(html ,prefix)

if this.download == True : this.downs(arr ,prefix);

if this.write == True : this.writeFile(arr);

except:

print "catch finally exception."

class Filter():

def __init__(this ,url ,arg):

this.arg = arg

this.url = url

def _getDomain(this):

url = this.url.split('/')

return url[0]+'//'+url[2]

def _getRealUrl(this ,domain, url):

if url[0] == '/' : return domain + url;

if 'http://' in url : return url

#==============须要处理的字符串链接...

return domain + '/' +url;

def execute(this ,html ,prefix):

_arg = this.arg; arr=[]; getRealUrl = this._getRealUrl;

its = re.finditer( _arg['regex'] ,html)

for match in its: arr.append(getRealUrl(this._getDomain() ,match.groups()[0]))

if _arg.has_key('custom') == True and _arg['custom'] != '' : _arg['custom'](arr ,prefix);

return arr

def paginList(arr ,prefix):

num = 1;

for x in arr:

Page(x ,'

' ,{

'download' : True,

'outpath' : 'f:/temp/'

}).start(prefix+'_'+str(num));

num+=1

Page("http://www.netbian.com/fengjing/" ,'

)"\s.*?\salt="(.*?)"\s.*?

' ,{

'custom' : paginList,

'pagin' : {

'start' : 2,

'end' : 10,

'rule' : 'http://www.netbian.com/fengjing/index_{page}.htm'

}

}).start()

2.执行例如以下

$ python getjpg.py

download-succeed        -> 1_1_1bdbc1d1628a1f0ebd5fc60055ee506e.jpg

download-succeed        -> 1_2_01b5b45171979aace617ab79299d7515.jpg

download-succeed        -> 1_3_5698c42371add40501a328ef2c753b4d.jpg

download-succeed        -> 1_4_f7219087ce29c474a777867b8e4755ed.jpg

download-succeed        -> 1_5_58bf8172ea8bbc4cee0a0f8240f2b289.jpg

download-succeed        -> 1_6_b4700f4bd96f90039ed662ebbf6c1f7c.jpg

download-succeed        -> 1_7_8a637b3362acddac4671d9ad02e4a93f.jpg

download-succeed        -> 1_8_f28e22908b68d6fbe42a15c4fcd62613.jpg

download-succeed        -> 1_9_03806c0b3d33cfc3a3eb4ea3bbe8ca9e.jpg

download-succeed        -> 1_10_cf26fb246e9b57c06e328af94e60450b.jpg

download-succeed        -> 1_11_7563610f39bd29b8381201b95eed2624.jpg

download-succeed        -> 1_12_8ccaccede13d0f377d0d8822243f3b6a.jpg

download-succeed        -> 1_13_c95a0207db67a334be4812cec25d7023.jpg

download-succeed        -> 1_14_71ce070aef91660e8dad60a5919ec505.jpg

download-succeed        -> 1_15_9a647a8f449cdb3208a561b4c9fe2ce6.jpg

download-succeed        -> 1_16_45d9992e3d5080cf14ef73da14066283.jpg

download-succeed        -> 1_17_7bd84ee7d6f5cb911a3b1dbc6e0775c4.jpg

download-succeed        -> 1_18_8397b9d434a187444c389ebff48bcfb5.jpg

download-succeed        -> 2_1_f14e658f2464769756039e1ff18d5693.jpg

download-succeed        -> 2_2_ad051a669008969800ccd324de056465.jpg

download-succeed        -> 2_3_6190ffe369199b95274100996b02359a.jpg

download-succeed        -> 2_4_f14dce28d960941781a12a57123076df.jpg

download-succeed        -> 2_5_c7fb3b6f700339e9f3c9ee02474211eb.jpg

download-succeed        -> 2_6_327f1a33b8c5989a2d014ea41565caef.jpg

...

3.结果例如以下