python实现搜索指定目录下文件及文件内搜索指定关键词的方法

本文实例讲述了python实现搜索指定目录下文件及文件内搜索指定关键词的方法。分享给大家供大家参考。具体实现方法如下:

#!/usr/bin/python -o
# -*- coding: utf-8 -*-
“””
sucht rekursiv in dateiinhalten und listet die fundstellen auf.
“””
__author__ = “jens diemer”
__license__ = “””gnu general public license v2 or above –
http://www.opensource.org/licenses/gpl-license.php”””
__url__ = “http://www.jensdiemer.de”
__version__ = “0.1”
import os, time, fnmatch
class search:
def __init__(self, path, search_string, file_filter):
self.search_path = path
self.search_string = search_string
self.file_filter = file_filter
print “search ‘%s’ in [%s]…” % (
self.search_string, self.search_path
)
print “_” * 80
time_begin = time.time()
file_count = self.walk()
print “_” * 80
print “%s files searched in %0.2fsec.” % (
file_count, (time.time() – time_begin)
)
def walk(self):
file_count = 0
for root, dirlist, filelist in os.walk(self.search_path, followlinks=true):
for filename in filelist:
for file_filter in self.file_filter:
if fnmatch.fnmatch(filename, file_filter):
self.search_file(os.path.join(root, filename))
file_count += 1
return file_count
def search_file(self, filepath):
f = file(filepath, “r”)
content = f.read()
f.close()
if self.search_string in content:
print filepath
self.cutout_content(content)
def cutout_content(self, content):
current_pos = 0
search_string_len = len(self.search_string)
for i in xrange(max_cutouts):
try:
pos = content.index(self.search_string, current_pos)
except valueerror:
break
content_window = content[ pos – content_extract : pos + content_extract ]
print “>>>”, content_window.encode(“string_escape”)
current_pos += pos + search_string_len
print
if __name__ == “__main__”:
search_path = r”c:\texte”
file_filter = (“*.py”,) # fnmatch-filter
search_string = “history”
content_extract = 35 # gr��e des ausschnittes der angezeigt wird
max_cutouts = 20 # max. anzahl an treffer, die angezeigt werden sollen
search(search_path, search_string, file_filter)

希望本文所述对大家的python程序设计有所帮助。

Posted in 未分类