python搜索指定目录中的文件 python在文件内搜索指定的关键词

发布时间:2020-03-11编辑:脚本学堂
本文分享一例python代码,用于在指定的目录中搜索文件,并可以在文件内搜索指定的关键词,真的很霸气的功能哦,有需要的朋友参考下吧。

本节主要内容:
python代码一例。
搜索指定目录中的文件,并可以在文件内搜索指定的关键词。

代码:
 

复制代码 代码示例:

#!/usr/bin/python -O
# -*- coding: UTF-8 -*-
#site: wwww.jb200.com
#

"""
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)