翻看自己以前写的程序,发现写过一个爬取盘多多百度云资源的东西,完全是当时想看变形金刚才自己写的,而且当时第一次接触python大概写了有2天才搞出来这个程序,学习python语言,可以看得出来那时候的代码写的真的low。虽然现在也不怎么样,哈哈,一直学习中,不做过多解释,上图上代码,因为变量的声明是什么我自己也忘了(手动傲娇),连写入文件当时都不会哈哈哈哈哈哈哈哈,也不知道class中可以通过init初始化,唉学习python原来我学到了这么多东西,感谢python
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
from bs4 import BeautifulSoup
import urllib
import requests
import re
adr = []
''''对搜素资源名字进行url编码'''
search_text = raw_input ( '请输入搜索资源名:' )
search_text = search_text.decode( 'gbk' )
search_text = search_text.encode( 'utf-8' )
search_text = urllib.quote(search_text)
''''获取文件地址'''
home = urllib.urlopen( 'http://www.panduoduo.net/s/name/' + search_text)
'''获取百度云地址'''
def getbaidu(adr):
for i in adr:
url = urllib.urlopen( 'http://www.panduoduo.net' + i)
bs = BeautifulSoup(url)
bs1 = bs.select( '.dbutton2' )
href = re. compile ( 'http\%(\%|\d|\w|\/\/|\/|\.)*' )
b = href.search( str (bs1))
name = str (bs.select( '.center' )).decode( 'utf-8' )
text1 = re. compile ( '\<h1\sclass\=\"center"\>[\d|\w|\D|\W]*\</h1\>' )
text2 = text1.search(name)
rag1 = re. compile ( '\>[\d|\w|\D|\W]*\<' )
if text2:
text3 = rag1.search(text2.group())
if text3:
print text3.group()
if b:
text = urllib.unquote( str (b.group())).decode( 'utf-8' )
print text
'''初始化'''
def init(adr):
soup = BeautifulSoup(home)
soup = soup.select( '.row' )
pattern = re. compile ( '\/r\/\d+' )
for i in soup:
i = str (i)
adress = pattern.search(i)
adress = adress.group()
adr.append(adress)
print 'running---------' init(adr)
getbaidu(adr)
|
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。
原文链接:http://www.jianshu.com/p/5290b9273fe3?utm_source=tuicool&utm_medium=referral