python批量获取html内body内容 python批量获取html内body内容的实例

# -*- coding:utf8 -*-
 
from bs4 import BeautifulSoup
import os
import os.path
import sys
reload(sys) 
sys.setdefaultencoding('utf8') 
 
 
def printPath(level,path):
	global allFileNum
	#所有文件夹，第一个字段是此目录的级别
	dirList = []
 
	#所有文件
	fileList = []
 
	#返回一个列表，其中包含在目录条目的名称
	files = os.listdir(path)
 
	#先添加目录级别
	dirList.append(str(level))
 
	for f in files:
		if(os.path.isdir(path+'/'+f)):
			#排除隐藏文件夹，因为隐藏文件夹过多
			if(f[0] == '.'):
				pass
			else:
				#添加隐藏文件夹
				dirList.append(f)
		if(os.path.isfile(path+'/'+f)):
			#添加文件
			fileList.append(f)
	return (dirList,fileList)
 
#将文件html文件抓取并写入指定txt文件
def getAndInsert(rootdir,savepath,path):
	global file_num
	f_list = os.listdir(rootdir+'/'+path)
	for i in f_list:
		temp = os.path.splitext(i)[0]
		for num in range(1,11):
			if(i==str(num)+'.html'):
				#print rootdir+'/'+path+'/'+i
				objFile = open(rootdir+'/'+path+'/'+i)
				soup = BeautifulSoup(objFile)
				arr = []
				for child in soup.body:
					arr.append(child)
				if os.path.exists(savepath+'/'+path):
					pass
				else:
					os.makedirs(savepath+'/'+path)
				f = open(savepath+'/'+path+'/'+temp+'.txt','w')
				for k,v in enumerate(arr):
					if k!=1:
						f.write(str(v))
				f.close()
				print path+'/'+i+' is running'
	file_num = file_num + 1
			
 
rootdir = '../zips2'
dirList,fileList = printPath(1,rootdir)
 
savepath = "../testC"
file_num = 0
 
for fn in dirList:
	if(fn == '1'):
		pass
	else:
		getAndInsert(rootdir,savepath,fn)
		print fn+' is ending'
print '一共完成'+str(file_num)+'个城市的提取'