python html转TXT python读取html指定区域文本内容转成txt文件

1、首先，通过python，去将读取遍历程序目录文件夹中，【html】文件夹里面的文件、文件

夹以及子目录、子目录里面的 ，获取到该目录下所有的【.html】文件后，返回一个list对象

2、遍历完成后得到一个html文件列表对象，将该列表交给html_to_txt方法，html_to_txt方法

里面循环逐个读取html文件中指定标签中

标签中

标签中的文字，和中指定标签

里面

标签的文字提取出来

3、读取到的文本内容输出到txt文件中，这里可以加上一个替换replace，把我们不需要的内

容替换之后，这里可以做多次替换，也可以加上换行之类的处理，再进行输出，可根据自己

的需求修改，如果有什么不明之处，可以提问

资源

main.py

```python
import glob
import os
import re
import pypandoc
from selectolax.parser import HTMLParser
from html.parser import HTMLParser

from lxml import etree

from Html_To_txt import html_to_txt


# 解析本地html,返回字典数据类型
def parse_html(file_path, vla=None):
    for ff in file_path:
        val = []
        with open(ff, 'r', encoding='gbk') as f:
            html = etree.HTML(f.read())
        Title = html.xpath("//*[@id='left']/div/div[2]/h1/text()")

        contents = html.xpath("//td[@class='info_content']/*")
        val.append(Title)

        for td in contents:
            val.append(td.text)
            a = html_for(td.xpath("./strong/a"))

            b = html_for(td.xpath("./strong/tail()"))
            vla.append(a.text)
            vla.append(b.text)
        txt = open(os.getcwd() + "\\txt\\" + ff.split('\\')[-1], 'w', encoding="utf-8")
        txt.write(val)
        txt.close()

        # res = {}
        # for div in divs:
        #     key = div.xpath("./span[1]/text()")[0].replace('/', '_')
        #     value = div.xpath("./span[2]/text()")[0]
        #     res[key] = value


def html_for(html_obj):
    aaa_ls = []
    if len(html_obj) > 2:
        for bbb in html_obj:
            if len(bbb) > 2:
                aaa_ls.append(html_for(bbb).text)
            else:
                aaa_ls.append(bbb.text)
    else:
        a = html_obj[0].text
        b = html_obj[0].tail
        aaa_ls.append(str(html_obj[0].text + html_obj[0].tail))
    return aaa_ls


def search_dir(pathstr, file_all=[]):
    files = os.listdir(pathstr)  # 得到文件夹下的所有文件名称
    # print(files)
    for file_str in files:  # 遍历该文件夹
        if os.path.isdir(pathstr + "\\" + file_str):  # 是子文件夹
            search_dir(pathstr + "\\" + file_str)
        else:  # 是文件

            if os.path.splitext(file_str)[1] == '.html':
                print(pathstr + "\\" + file_str)
                file_all.append(pathstr + "\\" + file_str)
    return file_all


# 按间距中的绿色按钮以运行脚本。
if __name__ == '__main__':
    path = os.getcwd() + r'\html'
    aaa = search_dir(path)
    html_to_txt(aaa)

Html_To_txt.py

import os

from lxml import etree

from sgmllib import SGMLParser


class GetIdList(SGMLParser):
    # def __init__(self, verbose=0):
    #     super().__init__(verbose)
    #     self.verbatim = 0
    #     self.getdata = False
    #     self.flag = False
    #     self.IDlist = []

    def reset(self):
        self.IDlist = []
        self.flag = False
        self.getdata = False
        self.verbatim = 0
        SGMLParser.reset(self)

    # def start_div(self, attrs):
    #     if self.flag:
    #         self.verbatim += 1  # 进入子层div了，层数加1
    #         return
    #     for k, v in attrs:  # 遍历div的所有属性以及其值
    #         if k == 'class' and v == 'entry-content':  # 确定进入了

    #             self.flag = True
    #             return
    #
    # def end_div(self):  # 遇到
    #     if self.verbatim == 0:
    #         self.flag = False
    #     if self.flag:  # 退出子层div了，层数减1
    #         self.verbatim -= 1

    def start_div(self, attrs):
        if self.flag:
            self.verbatim += 1  # 进入子层td了，层数加1
            return
        for k, v in attrs:  # 遍历div的所有属性以及其值
            if k == 'class' and v == 'article-content':  # 确定进入了

                self.flag = True
                return

    def end_div(self):  # 遇到
        if self.verbatim == 0:
            self.flag = False
        if self.flag:  # 退出子层td了，层数减1
            self.verbatim -= 1

    # def start_td(self, attrs):
    #     if self.flag:
    #         self.verbatim += 1  # 进入子层td了，层数加1
    #         return
    #     for k, v in attrs:  # 遍历div的所有属性以及其值
    #         if k == 'class' and v == 'info_content':  # 确定进入了

    #             self.flag = True
    #             return
    #
    # def end_td(self):  # 遇到
    #     if self.verbatim == 0:
    #         self.flag = False
    #     if self.flag:  # 退出子层td了，层数减1
    #         self.verbatim -= 1

    def start_h1(self, attrs):
        if not self.flag:
            return
        self.getdata = True

    def end_h1(self):  # 遇到

        if self.getdata:
            self.getdata = False

    def start_p(self, attrs):
        if not self.flag:
            return
        self.getdata = True

    def end_p(self):  # 遇到

        if self.getdata:
            self.getdata = False

    def handle_data(self, text):  # 处理文本
        if self.getdata:
            self.IDlist.append(text)

    def printID(self, new_file):

        f = open(os.getcwd() + "\\txt\\" + (new_file.split('\\'))[-1] + '.txt', 'w', encoding='gbk')
        j = 0

        for i in self.IDlist:
            print(i)
            if '。' in i or j == 0:
                f.write(i + '\n')
                j += 1
            else:
                f.write(i )

        ##import urllib2


##import datetime
##vrg = (datetime.date(2012,2,19) - datetime.date.today()).days
##strUrl = 'http://www.nod32id.org/nod32id/%d.html'%(200+vrg)
##req = urllib2.Request(strUrl)#通过网络获取网页
##response = urllib2.urlopen(req)
##the_page = response.read()
def html_to_txt(html_list):
    for a in html_list:
        the_page = a
        ff = open(the_page, 'r',encoding='utf-8')
        html = ff.read()
        lister = GetIdList()
        lister.feed(html)
        lister.printID(a)