Python 使用xpath匹配html内容并生成CSV文件

最新推荐文章于 2021-05-06 08:34:42 发布

原创最新推荐文章于 2021-05-06 08:34:42 发布 · 371 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#csv #python #xpath

Python 专栏收录该内容

3 篇文章

订阅专栏

本文介绍了一种使用Python批量读取HTML文件，并通过lxml库的XPath解析技术来提取标题、内容、来源、时间和作者等关键信息的方法。该方法利用CSV模块将提取到的信息存储为CSV文件，便于进一步的数据处理和分析。

#-- coding: utf-8 --
import os
import re
import csv
from lxml import html
#生成CSV文件
def get_list_dir():
    headers = ('标题', '内容', '来源', '时间', '作者')
    with open('D:/Python/PythonProjects/TestDemo/article/31530942.csv', 'w', encoding='utf-8-sig') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(headers)
    dir_aim = "D:/Python/PythonProjects/TestDemo/article"
    for filename in os.listdir(dir_aim):
        #print(filename)
        article = get_article_content(filename)
        if article:
            with open('D:/Python/PythonProjects/TestDemo/article/31530942.csv', 'a+', encoding='utf-8-sig') as csvfile:
                writer = csv.writer(csvfile)
                writer.writerow(article)
#读取html文件用xpath解析文件返回结果
def get_article_content(fileName):
    try:
        with open('D:/Python/PythonProjects/TestDemo/article/'+fileName, 'r', encoding='utf-8') as f:
            content = f.read()
            etree = html.etree
            ht = etree.HTML(content)
            title = "".join(ht.xpath("/html/body/div[5]/h1/text()"))
            content = "".join(ht.xpath("/html/body/div[5]/div[2]/p/text()")).replace("\n","")
            source = "".join(ht.xpath("/html/body/div[5]/div[1]/text()"))
            if source:
                source = re.search(r"来源：(.*?)\s",source)
                if source:
                    source = source.group().replace("来源：", "")
                else:
                    source = ""
            else:
                source = ""
            time = "".join(ht.xpath("/html/body/div[5]/div[1]/text()"))
            if time:
                time = re.search(r"时间：(.*?)$", time)
                if time:
                    time = time.group().replace("时间：", "")
                else:
                    time = ""
            else:
                time = ""
            edit = "".join(ht.xpath("/html/body/div[5]/div[3]/text()"))
            if edit:
                edit = re.search(r"责编：(.*?)\s",edit)
                if edit:
                    edit = edit.group().replace("责编：", "")
                else:
                    edit = ""
            else:
                edit =""
            return (title, content, source, time, edit)
    except Exception as e:
        print(e)
get_list_dir()

a+ 是追加方式写入