"""
Description:正則清洗HTML數據
Author:
Prompt:?code?in?python3?env
"""
"""
???re.I???使匹配對大小寫不敏感
???re.L???做本地化識別（locale-aware）匹配
???re.M???多行匹配，影響^(開頭)和$(結尾)
???re.S???匹配包含換行在內的所有字符
???re.U???根據Unicode字符集解析字符，這個標志影響?\w,?\W,?\b,?\B
???re.X???該標志通過給予你更靈活的格式以便你將正則表達式寫得更加
"""
import?re

#?處理HTML標簽文本
#?@param?htmlstr?html字符串


def?filter_tags(htmlstr):
???#?過濾doc_type
???htmlstr?=?'?'.join(htmlstr.split())
???re_doctype?=?re.compile(r'<!DOCTYPE?.*?>',?re.S)
???res?=?re_doctype.sub('',?htmlstr)

???#?過濾CDATA
???re_cdata?=?re.compile(?r'//<!CDATA\[[?>]?//\]?>',?re.I)
???res?=?re_cdata.sub('',?res)

???#?Script
???re_script?=?re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>',?re.I)
???res?=?re_script.sub('',?res)

???#?注釋
???re_script?=?re.compile('<!--.*?-->',?0)
???res?=?re_script.sub('',?res)

???#?換行符
???re_br?=?re.compile('<br\n*?/?>')
???res?=?re_br.sub('\n',?res)

???#?HTML?標簽
???re_lable?=?re.compile('</?\w[^>]*>')
???res?=?re_lable.sub('',?res)

???#?轉義字符
???re_esc?=?re.compile('&.*?;')
???res?=?re_esc.sub('',?res)

???#?空格處理
???re_blank?=?re.compile('\s+')?#?\s包含?\t?\n?\r?\f?\v
???res?=?re_blank.sub('?',?res)

???#?超鏈接處理
???re_http?=?re.compile(r'(http://.+.html)')
???res?=?re_http.sub('?',?res)

???d?=?lambda?pattern,?flags=0:?re.compile(pattern,?flags)
???for?re_type?in?re_mate:
??????re_type?=?d(*re_type)
??????res?=?re_type.sub('?',?res)
???return?res

def?read_file(read_path):
???str_doc?=?''
???with?open(read_path,?'r',?encoding='utf-8')?as?f:
??????str_doc?=?f.read()
???return?str_doc


if?__name__?==?'__main__':
???str_doc?=?read_file(r'../data/html/re.html')
???res?=?filter_tags(str_doc)
???#?print(res)


???with?open(r'../data/html/test.html',?'w',?encoding='utf-8')?as?f:
??????f.write(res)
???print('No?Exception')?#?我是通過另一個編輯器進行打開預覽的

這是我的筆記

https://github.com/bainingchao/DataProcess