Python用python-docx抓取公众号文章写入word

一、安装包

pip3 install python-docx

二、了解python-docx

from docx import Document
from docx.shared import Inches

document = Document()

#添加标题，并设置级别，范围：0 至 9，默认为1
document.add_heading('Document Title', 0)

#添加段落，文本可以包含制表符（\t）、换行符（\n）或回车符（\r）等
p = document.add_paragraph('A plain paragraph having some ')
#在段落后面追加文本，并可设置样式
p.add_run('bold').bold = True
p.add_run(' and some ')
p.add_run('italic.').italic = True

document.add_heading('Heading, level 1', level=1)
document.add_paragraph('Intense quote', style='Intense Quote')

#添加项目列表（前面一个小圆点）
document.add_paragraph(
    'first item in unordered list', style='List Bullet'
)
document.add_paragraph('second item in unordered list', style='List Bullet')

#添加项目列表（前面数字）
document.add_paragraph('first item in ordered list', style='List Number')
document.add_paragraph('second item in ordered list', style='List Number')

#添加图片
document.add_picture('monty-truth.png', width=Inches(1.25))

records = (
    (3, '101', 'Spam'),
    (7, '422', 'Eggs'),
    (4, '631', 'Spam, spam, eggs, and spam')
)

#添加表格：一行三列
# 表格样式参数可选：
# Normal Table
# Table Grid
# Light Shading、 Light Shading Accent 1 至 Light Shading Accent 6
# Light List、Light List Accent 1 至 Light List Accent 6
# Light Grid、Light Grid Accent 1 至 Light Grid Accent 6
# 太多了其它省略...
table = document.add_table(rows=1, cols=3, style='Light Shading Accent 2')
#获取第一行的单元格列表
hdr_cells = table.rows[0].cells
#下面三行设置上面第一行的三个单元格的文本值
hdr_cells[0].text = 'Qty'
hdr_cells[1].text = 'Id'
hdr_cells[2].text = 'Desc'
for qty, id, desc in records:
    #表格添加行，并返回行所在的单元格列表
    row_cells = table.add_row().cells
    row_cells[0].text = str(qty)
    row_cells[1].text = id
    row_cells[2].text = desc

document.add_page_break()

#保存.docx文档
document.save('demo.docx')

三、公众号写入word

# -*- coding:utf-8 -*- 
"""
Author：SPIDERMAN
Time: 2021/2/8 
Software: PyCharm
"""
import time
from scrapy import Selector
import re
from docx import Document
from docx.shared import Inches
import requests
from docx.oxml.ns import qn
from docx.shared import Pt,RGBColor
header = {
    "Host": "mp.weixin.qq.com",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
    "Accept-Encoding": "gzip, deflate, br",
    "Connection": "keep-alive"
}

def get_biz_html(url):
    """
    获取公众号的页面
    :param url: 
    :return: 
    """
    res = requests.get(url=url,timeout=8,headers=header).text
    contents = Selector(text=res).css('#js_content')
    re_title = re.compile('property="og:title".*?content="(.*?)"',re.S)
    re_time = re.compile(',n="(.*?)",',re.S)
    re_img = re.compile('property="og:image".*?content="(.*?)".*?/>')
    re_des = re.compile('name="description".*?content="(.*?)".*?/>')
    try:
        #构建存储字典
        item = {}
        #公众号标题
        title = re.findall(re_title,res)[0].strip()
        #公众号作者
        source = Selector(text=res).css('#js_name::text').extract_first().strip()
        #公众号链接
        url = url
        #公众号发布时间
        news_time = re.findall(re_time,res)[0]
        if news_time:
            news_time=time.strftime(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(int(news_time))))
        #公众号封面
        newsImage = re.findall(re_img,res)[0].strip()
        try:
            newsDes = re.findall(re_des,res)[0].strip()
        except:
            newsDes = ''
        content = contents.extract_first()
        get_html_item(title,content,source,news_time)
    except Exception as e:
        print('[Exception]:'+str(e))
        pass

def get_html_item(title,contents,source,news_time):
    """
    将文章正文分段
    :param title: 
    :param contents: 
    :param source: 
    :param news_time: 
    :return: 
    """
    print('[INFO]:'+title)
    print('[INFO]:'+contents)

    content_list =[]
    content_set = set()
    contents = Selector(text=contents).css('#js_content *')
    item = {}
    for content in contents:
        # print(content.extract())

        if 'img' in content.extract():
            sub_txt = sub_html(content.extract())
            if sub_txt:
                sub_txt = sub_txt.strip()
                if sub_txt not in content_set:
                    content_set.add(sub_txt)
                    text = sub_txt.strip()
                    content_list.append({'text':text})
            img = content.css('img::attr(data-src)').extract_first()
            if img and img not in content_set:
                content_list.append({'img': img.strip()})
                content_set.add(img)
        else:
            sub_txt = sub_html(content.extract())
            if sub_txt:
                sub_txt = sub_txt.strip()
                if sub_txt not in content_set:
                    content_set.add(sub_txt)
                    text = sub_txt.strip()
                    content_list.append({'text': text})


    print('[INFO]:html_to_word')
    html_to_word(title,content_list,source,news_time)

def sub_html(text):
    """
    替换标签
    :param text: 
    :return: 
    """
    text = re.sub(re.compile('<.*?>'),'',text)
    return text
def html_to_word(title,contents,source,news_time):
    """
    写入wrod
    :param title: 
    :param contents: 
    :param source: 
    :param news_time: 
    :return: 
    """
    document = Document()
    document.styles['Normal'].font.name = u'宋体'
    document.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体')
    document.styles['Normal'].font.size = Pt(10.5)
    document.styles['Normal'].font.color.rgb = RGBColor(0, 0, 0)
    #添加标题，并设置级别，范围：0 至 9，默认为1
    document.add_heading(title, 0)
    #添加段落，文本可以包含制表符（\t）、换行符（\n）或回车符（\r）等
    document.add_paragraph('{source}                     {news_time} '.format(source=source,news_time=news_time)).italic = True
    for content in contents:
        try:
            img =content['img']
            requset_img(img)
            document.add_picture('1.jpg', width=Inches(5))
        except:
            text = content['text']
            document.add_paragraph(text)
    document.add_page_break()

    #保存.docx文档
    document.save('{}.docx'.format(title))
    print('[INFO]:{}.docx is ok'.format(title))

    # document.save('{}.docx'.format(title))
    # print('{}.docx is ok'.format(title))

def img_parse(response):
    with open('1.jpg', 'wb') as img:
        img.write(response)

def requset_img(url):
    response = requests.get(url=url)
    img_parse(response.content)


if __name__ == '__main__':
    get_biz_html('https://mp.weixin.qq.com/s/SR7-VuRNH4h8W2MrluSjiA')

同学们可以自己运行一下

console.log("公众号:虫术")
console.log("wx:spiderskill")
欢迎大家前来交流