python BeautifulSoup基本用法

#coding:utf-8
import os
from bs4 import BeautifulSoup
#jsp 路径
folderPath = "E:/whm/google/src_jsp"

for dirPath,dirNames,fileNames in os.walk(folderPath):
    for fileName in fileNames:
        if fileName.endswith(".jsp"):
            soup=BeautifulSoup(open(os.path.join(dirPath,fileName)),"html.parser")
            if(soup.header is not None):
                soup.header.extract()
            #属性选择器。。。只能选择出第一个符合规则的元素
            if(soup.find(attrs={‘role‘:‘banner‘}) is not None):
                soup.find(attrs={‘role‘:‘banner‘}).extract()
            if(soup.find(attrs={‘class‘:"col-xs-3"}) is not None):
                soup.find(attrs={‘class‘:"col-xs-3"}).extract()
            with open(os.path.join(dirPath,fileName),"w+") as file:
                #pretify()方法返回一个美化过的html 字符串 encode(‘utf-8‘)指定编码--
                file.write(soup.prettify(formatter=None).encode(‘utf-8‘))

处理jsp页面会出现bug。。。所以。。不要使用BeautifulSoup处理 jsp和php等脚本页面。。。需要用正则来写。。。这是我摸索半天得来的结论。。。。。

时间： 2024-10-04 12:47:21

python BeautifulSoup基本用法的相关文章

python   name=='main' 用法

python 文件的后缀为.py,比如 name.py python 文件可以直接执行,也可以被导入.调用,比如import name; script 1: #!/bin/python # Filename:name.py if __name__=='__main__': print 'This program is being run by itself' else: print 'I am being imported from another module' script

python之函数用法capitalize()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法capitalize() #capitalize() #说明:将字符串的第一个字母变成大写,其他字母变小写. ''' capitalize(...) S.capitalize() -> string Return a copy of the string S with only its first character capitalized. ''' #案例 str='xiaoden

python之函数用法setdefault()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法setdefault() #D.get(k,d) #说明:k在D中,则返回 D[K],如果k不在D中,则返回d值 #D.get(k,d), also set D[k]=d if k not in D ''' >>> help(dict.setdefault) Help on built-in function setdefault: setdefault(...) D.set

python之函数用法islower()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法islower() #http://www.runoob.com/python/att-string-islower.html #islower() #说明:检测字符串是否都由小写字母组成 str = "THIS is string example....wow!!!" print str.islower()#False str = "this is string

python之函数用法xrange()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法xrange() #xrange() #说明:返回一个生成器 #xrange做循环的性能比range好,尤其是返回很大的时候.除非要返回一个列表,则用range. ''' class xrange(object) | xrange(stop) -> xrange object | xrange(start, stop[, step]) -> xrange object | | Li

python之函数用法startswith()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法startswith() #http://www.runoob.com/python/att-string-startswith.html #startswith() #说明:返回布尔值,用于检查字符串是否是以指定子字符串开头,如果是则返回 True,否则返回 False. ''' startswith(...) S.startswith(prefix[, start[, end]]

python之函数用法globals()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法globals() #globals() #说明:在当前作用域下,查看全局变量 ''' globals(...) globals() -> dictionary Return the dictionary containing the current scope's global variables. ''' #案例 b='xiaodeng' print globals#<buil

python之函数用法setattr

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法__setattr__ #http://www.cnblogs.com/hongfei/p/3858256.html #用__setattr__函数重构方法 class Fruit(): def __init__(self,color,price): self.__color = color self.__price = price def __setattr__(self,name

python之函数用法get()

# -*- coding: utf-8 -*- #python 27 #xiaodeng #python之函数用法get() #http://www.runoob.com/python/att-dictionary-get.html #dict.get(key, default=None) #说明:返回指定键的值,如果值不在字典中返回默认值. #key:要查找的键 #default:如果指定键的值不存在时,返回该默认值值 ''' >>> help(d.get) Help on built