python模块 - re模块使用示例

http://blog.csdn.net/pipisorry/article/details/46619179

re模块匹配规则见：http://blog.csdn.net/pipisorry/article/details/25909899

python正则表达式匹配年月日

(?:\d{4}[年./]|\d{2}年)(?:(?<!\d)(?:[1-9]|1[0-2])(?!\d)[月./])?(?:\d{1,2}[日号]{0,1})?|(?:\d{4}[年./]|\d{2}年)?(?:(?<!\d)(?:[1-9]|1[0-2])(?!\d)[月./])(?:\d{1,2}[日号]{0,1})?|(?:\d{4}[年./]|\d{2}年)?(?:(?<!\d)(?:[1-9]|1[0-2])(?!\d)[月./])?(?:\d{1,2})[日号]|(?:今|明|后)(?:天|日|晚)|明天的明天|(?:月|年)(?:底|末)|(?:上个?|下个?|这个?)?(?:周|星期)(?:几|\d+|[一二三四五六七日天]|末)|(?:上个?|下个?|这个?)(?:周|星期)|\d+[日天]?[-于到至－]\d+[日天]|(?:\d{1,2})多?天(?:之?后)?|(?:[一二三四五六七]|\d+)(?:周|个?星期|个月|年)

月：(?<!\d)(?:[1-9]|1[0-2])(?!\d)月

python正则表达式进行日志分析

日志分析时，假设给定的字符串：
char str = “10.10.1.1 [2015/04/22 +0800] /ab/cd/？test0=123&test2=234 xxxx”; 要从中获取2015/04/22、/ab/cd/和234等值。

str = “10.10.1.1 [2015/04/22 +0800] /ab/cd/？test0=123&test2=234 xxxx”
print(re.findall(“\d{4}/\d{2}/\d{2}|/\w{2}/\w{2}|(?<=test2=)\d+”, str))

 

用urllib2、re、os 模块下载文件的脚本

!/usr/bin/env python
importurllib2
importre
importos
URL=’http://image.baidu.com/channel/wallpaper’
read=urllib2.urlopen(URL).read()
pat =re.compile(r’src=\’#\’” //.+?.js”>’)
urls=re.findall(pat,read)
fori inurls:
url=i.replace(‘src=\’#\’” /code>,”).replace(‘”>’,”)
try:
iread=urllib2.urlopen(url).read()
name=os.path.basename(url)
with open(name,’wb’) as jsname:
jsname.write(iread)
except:

printurl,”url error”

 

将所有文档中不同问题分别汇总到同一个文件中

 

def shift():
    '''
    筛选所有人不同问题的答案到对应的文件中
    :return:
    '''
    INPUT_DIR = r'C:\Users\pi\Desktop\txts'
    ANSWER_DIR = r'C:\Users\pi\Desktop\answers'
    if not path.exists(ANSWER_DIR):
        makedirs(ANSWER_DIR)

    questions = ['在计科四班度过大学四年是一种怎样的体验', '对班上的哪位同学第一印象最深刻，简述原因', '简述让你印象深刻的班上某位同学的一件小事', '想对你的室友说什么', '大学你最遗憾的事',
                 '最难忘或最感动或最想珍惜的一件事或人', '马上要毕业了，此刻的你内心是一种怎样的体验', '想对你暗恋or前女友or现任恋人说什么', '（写完后记得将文档重命名加上你的姓名）']
    answer_filenames = [str(i) + '.txt' for i in range(len(questions) - 1)]

    for doc_name in listdir(INPUT_DIR):
        print(doc_name)
        doc_full_name = path.join(INPUT_DIR, doc_name)
        # print(doc_full_name)
        open(doc_full_name)
        with open(doc_full_name) as doc_file:
            # file_str = ''.join(doc_file.read().split('\n'))
            file_str = doc_file.read()
            # print(file_str)
            for cur_question, post_question, answer_filename in zip(questions, questions[1:], answer_filenames):
                patten = cur_question + '[:：](.+)' + post_question
                try:
                    answer = re.findall(patten, file_str, re.S)[0]
                    # print(answer)
                    answer = re.split('\.|\d+', doc_name)[1] + '：' + answer.strip() + '\n'
                    print(answer)
                    with open(path.join(ANSWER_DIR, answer_filename), 'a') as answer_file:
                        answer_file.write(answer)
                except:
                    print(RED, "Error in file:", DEFAULT, doc_full_name, RED, "question:", DEFAULT, cur_question)
            #     break
            # break

from:http://blog.csdn.net/pipisorry/article/details/46619179

 

ref:python模块 - re模块

python正则表达式