提取公众号ppt成为自己的ppt

注意：这种方法提取出来的ppt全部是图片形式；

import requests
from bs4 import BeautifulSoup
import datetime
import os
from docx import Document
from docx.shared import Cm as word_Cm
from pptx import Presentation
from pptx.util import Cm as ppt_Cm

# 图片格式列表
pic_format_list = []


# 创建文件夹
def create_file():
# 获取系统时间
curr_time = datetime.datetime.now()

# 将时间格式化为字符生成时间戳到时候给文件夹命名用
path = datetime.datetime.strftime(curr_time, '%Y%m%d%H%M')

# 检查是否存在这个文件夹
if not os.path.exists(path):
# 不存在则创建
os.mkdir(path)

# 获取当前工作目录并加上之前的时间生成文件夹路径
dirname = os.path.join(os.getcwd(), path)
return dirname


# 获取微信公众号图片
def get_picture(url):
headers = {
'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1'
}
# 向刚才输入的公众号链接里面发送请求
req = requests.get(url=url, headers=headers).content.decode()
# 用BeautifulSoup解析网页
soup = BeautifulSoup(req, 'lxml')
res = soup.select('img') # 获取该网页中所有的图片标签
a = 0
# 获取图片保存路径
base_path = create_file()
# 遍历所有的图片标签
for i in res:
if i.get("data-src"):
pic_format_list.append(i.get("data-type"))
try:
# 拼接路径+a.jpg a是等于数字 每添加一个 a自增一 相当于是给图片命名 并且以二进制的形式写入
img_path = os.path.join(base_path, f'{a}.{i.get("data-type")}')
with open(img_path, 'wb') as f:
# 向这个图片发送请求 并将图片的二进制写入
f.write(requests.get(url=i.get("data-src"), headers=headers).content)
a += 1 # a自增一
except Exception as e:
print(f"该链接为空自动跳过！错误：{e}")
print(f"此次一共成功保存图片{a}张")


# 生成word文档
def Generate_word(file_name):
Doc = Document()

# 设置页面边距
sec = Doc.sections[0] # sections对应文档中的“节”
sec.left_margin = word_Cm(0)
sec.right_margin = word_Cm(0)
sec.top_margin = word_Cm(0)
sec.bottom_margin = word_Cm(0)

# 获取图片保存路径
base_path = create_file()

# 插入图片
for i in range(len(pic_format_list)):
path = os.path.join(base_path, f'{i}.{pic_format_list[i]}')
Doc.add_picture(path, width=word_Cm(21.88), height=word_Cm(29))

Doc.save(f'./{file_name}.docx')


# 生成ppt
def Generate_ppt(file_name):
PPT = Presentation()

# 获取图片保存路径
base_path = create_file()

# 插入图片
for i in range(len(pic_format_list)):
path = os.path.join(base_path, f'{i}.{pic_format_list[i]}')
ppt_slide = PPT.slides.add_slide(PPT.slide_layouts[6]) # 空白版式
ppt_slide.shapes.add_picture(path, left=ppt_Cm(0), top=ppt_Cm(0), height=ppt_Cm(19))

PPT.save(f'./{file_name}.pptx')


if __name__ == '__main__':
url = input("请输入微信公众号url：")
file_name = input("请设置文档名称：")
get_picture(url) # 获取微信公众号图片
print("Saving......")
# Generate_word(file_name) # 生成word
Generate_ppt(file_name) # 生成ppt
print(pic_format_list)
print("文档创建成功！")