项目1：自动添加标签

最新推荐文章于 2022-03-31 15:09:49 发布

mktb

最新推荐文章于 2022-03-31 15:09:49 发布

阅读量245

点赞数

分类专栏： python 文章标签： python

本文链接：https://blog.csdn.net/weixin_44699062/article/details/108074488

版权

python 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

Python基础教程项目1：自动添加标签

代码仓库：https://github.com/mktb-nobug/Beginning-Python.git

初次实现：

util.py

def lines(file):
    for line in file:
        yield line
        yield '\n'


def blocks(file):
    block = []
    for line in lines(file):
        if line.strip():
            block.append(line)
        elif block:
            yield ''.join(block).strip()
            block = []

simple_mark.py

import sys, re
from util import *

print('<html><head><title>...</title><body>')

fin = open('test_input.txt', 'r')
old = sys.stdin
sys.stdin = fin

fout = open('test_output.html', 'w')
old_out = sys.stdout
sys.stdout = fout
title = True
for block in blocks(sys.stdin):
    block = re.sub(r'\*(.+?)\*', r'<em>\1</em>', block)
    if title:
        print('<h1>')
        print(block)
        print('</h1>')
        title = False
    else:
        print('<p>')
        print(block)
        print('</p>')

print('</body></html>')

再次实现：

main.py

import sys, re
from handlers import *
from util import *
from rules import *


class Parser:
    def __init__(self, handler):
        self.handler = handler
        self.rules = []
        self.filters = []

    def addRule(self, rule):
        self.rules.append(rule)

    def addFilter(self, pattern, name):
        def filter(block, handler):
            return re.sub(pattern, handler.sub(name), block)

        self.filters.append(filter)

    def parse(self, file):
        self.handler.start('document')
        for block in blocks(file):
            for filter in self.filters:
                block = filter(block, self.handler)
            for rule in self.rules:
                if rule.condition(block):
                    if rule.action(block, self.handler):
                        break

        self.handler.end('document')


class BasicTextParser(Parser):
    def __init__(self, handler):
        Parser.__init__(self, handler)
        self.addRule(ListRule())
        self.addRule(ListItemRule())
        self.addRule(TitleRule())
        self.addRule(HeadingRule())
        self.addRule(ParagraphRule())

        self.addFilter(r'\*(.+?)\*', 'emphasis')
        self.addFilter(r'(http://[\.a-zA-Z/]+)', 'url')
        self.addFilter(r'([\.a-zA-Z]+@[\.a-zA-Z]+[a-zA-Z])', 'mail')


# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    fin = open('test_input.txt', 'r')
    old_in = sys.stdin
    sys.stdin = fin

    fout = open('test_output.html', 'w')
    old_out = sys.stdout
    sys.stdout = fout

    handler = HTMLRenderer()
    parser = BasicTextParser(handler)

    parser.parse(sys.stdin)

handlers.py

class Handler:
    def callback(self, prefix, name, *args):
        method = getattr(self, prefix + name, None)
        if callable(method):
            return method(*args)

    def start(self, name):
        self.callback('start_', name)

    def end(self, name):
        self.callback('end_', name)

    def sub(self, name):
        def substitution(match):
            result = self.callback('sub_', name, match)
            if result is None:
                match.group(0)
            return result

        return substitution


class HTMLRenderer(Handler):
    def start_document(self):
        print('<html><head><title>...</title></head><body>')

    def end_document(self):
        print('</body></html>')

    def start_paragraph(self):
        print('<p>')

    def end_paragraph(self):
        print('</p>')

    def start_heading(self):
        print('<h2>')

    def end_heading(self):
        print('</h2>')

    def start_list(self):
        print('<ul>')

    def end_list(self):
        print('</ul>')

    def start_listitem(self):
        print('<li>')

    def end_listitem(self):
        print('</li>')

    def start_title(self):
        print('<h1>')

    def end_title(self):
        print('</h1>')

    def sub_emphasis(self, match):
        return '<em>{}</em>'.format(match.group(1))

    def sub_url(self, match):
        return '<a href="{}">{}</a>'.format(match.group(1), match.group(1))

    def sub_mail(self, match):
        return '<a href="mailto:{}">{}</a>'.format(match.group(1), match.group(1))

    def feed(self, data):
        print(data)

rules.py

class Rule:
    def action(self, block, handler):
        handler.start(self.type)
        handler.feed(block)
        handler.end(self.type)
        return True


class HeadingRule(Rule):
    type = "heading"

    def condition(self, block):
        return not '/n' in block and len(block) <= 70 and not block[-1] == ':'


class TitleRule(HeadingRule):
    type = 'title'
    first = True

    def condition(self, block):
        if not self.first:
            return False
        self.first = False
        return HeadingRule.condition(self, block)


class ListItemRule(Rule):
    type = 'listitem'

    def condition(self, block):
        return block[0] == '-'

    def action(self, block, handler):
        handler.start(self.type)
        handler.feed(block[1:].strip())
        handler.end(self.type)
        return True


class ListRule(ListItemRule):
    type = 'list'
    inside = False

    def condition(self, block):
        return True

    def action(self, block, handler):
        if not self.inside and ListItemRule.condition(self, block):
            handler.start(self.type)
            self.inside = True
        elif self.inside and not ListItemRule.condition(self, block):
            handler.end(self.type)
            self.inside = False
        return False


class ParagraphRule(Rule):
    type = 'paragraph'

    def condition(self, block):
        return True

mktb

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
项目1：自动添加标签

Python基础教程项目1：自动添加标签代码仓库：https://github.com/mktb-nobug/Beginning-Python.git初次实现：util.pydef lines(file): for line in file: yield line yield '\n'def blocks(file): block = [] for line in lines(file): if line.strip()
复制链接

扫一扫