下载 pdf、ppt 和 zip 文件中抓取的图像

Question

我已经尝试了很多次将图像下载为 pdf ppt 或 zip 文件，但我没有得到正确的解决方案。希望你能帮助我。附上整个代码，您可以修改它。

我正在尝试抓取slideshare.net并将图像分别输出为pdf、ppt和zip文件。 但我在做的过程中遇到了很多错误。我正在烧瓶应用程序中执行此操作。

Answer 1

不知道是否鼓励在stackoverflow中提供完整的代码。我已经在这里使用 BeautifulSoup 模块完成了。其余的解释我在代码中作为注释给出。

import requests
from bs4 import BeautifulSoup as bs
import os
from fpdf import FPDF
from PIL import Image
import zipfile as zp

url = '<Your URL here>'
response = requests.get(url)
soup = bs(response.content, 'html.parser')

# Find all image tags
img_tags = soup.find_all('img')

# Create 2 lists of image_urls and file names of the image file. 
img_urls = []
file_names = []

# Iterate thru img_tags
for x in img_tags:

    # Get image_urls and append to the list img_urls
    img_url = x.get('src')
    if img_url:
        img_urls.append(img_url)
        
        #to get the file name from the image url,
        
        #reverse the image url
        file_name = img_url[::-1]
        
        # get the reversed file name by slicing
        if file_name.find('/') == 0:file_name == file_name[1:]
        idx = file_name.find('/')
        file_name = file_name[:idx]
        
        #reverse to get the file name, append to list file_names
        file_name = file_name[::-1]
        file_names.append(file_name)

# Download Images
# Iterate thru img_urls
for i, x in enumerate(img_urls):

    # Get the image_file content as binary
    img_data = requests.get(x).content
    
    #create a file with file names stored in the list file_names write and save the img content as binary
    with open(f'images/{file_names[i]}', 'wb') as img_file:
        img_file.write(img_data)        
        
# Create a directory to save in your local computer
if not os.path.exists('images'): os.makedirs('images')

#To save as pdf
pdf = FPDF()

# Iterate thru img_urls
for i in range(len(img_urls)):
    pdf.add_page()
    pdf.image(f'images/{file_names[i]}', x=10, y=10, w=pdf.w - 20)
pdf.output('images.pdf', 'F')

# Create a PPT with the Images
prs = Presentation()


for i in range(len(img_urls)):
    slide_layout = prs.slide_layouts[5]  # Use a blank slide layout
    slide = prs.slides.add_slide(slide_layout)
    img_path = f'images/{file_names[i]}'
    slide.shapes.add_picture(img_path, Inches(1), Inches(1), width=Inches(8), height=Inches(6))    
prs.save('images.pptx')

# Create zipfile
with zp.ZipFile('images.zip', 'w') as zipf:
    for i in range(len(img_urls)):
        img_path = f'images/{file_names[i]}'
        zipf.write(img_path, os.path.basename(img_path))
        
        
        
        
    
            
    
   

    


   
prs.save('images.pptx') 
 
# Save image as Pdfs
          
    pdf.add_page()
    pdf.image(f'images/{file_name}', x=10, y=10, w=pdf.w - 20)
    
pdf.output('images.pdf', 'F')       
    
    img_path = f'images/{file_name}'
    slide.shapes.add_picture(img_path, Inches(1), Inches(1), width=Inches(8), height=Inches(6))
    
    with zipfile.ZipFile('images.zip', 'w') as zipf:
        img_path = f'images/{file_name}'
slide_layout = prs.slide_layouts[5]  # Use a blank slide layout
slide = prs.slides.add_slide(slide_layout)