Summary
As we all know, the content on the web page is now. If you encounter excellent resources and articles, if you don’t save them as soon as possible, they may be blocked or removed from the shelves after a while, so under this premise, how to save the required content with a relatively complete format and template Come down, has become our compulsory course.
The article provides you with how to quickly save the content of the specified Zhihu Q&A reply.
Find the specified content to be extracted
It must be extracted according to the specified answer link, such as the following picture
What should I do if there are links with only questions and no answers?
Save to the answer according to what you need, find the personal homepage of the answerer, and find the answer according to the time of answering the question
After clicking the title of the question, you can jump to the link address answered by the user, and you can extract it
Extract the content of the article according to the link information, the code is as follows:
import os
import requests
from bs4 import BeautifulSoup
import base64
import imghdr
import sys
"""用于爬取知乎上面的指定回答"""
def fetch_url_content(url):
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
response = requests.get(url, headers=headers)
response.raise_for_status()
response.encoding = response.apparent_encoding
return response.text
except Exception as e:
print(f"获取URL内容时发生错误: {url}。错误信息: {e}")
return None
def extract_answer_content(html_content):
soup = BeautifulSoup(html_content, 'html.parser')
answer = soup.find('div', class_='RichContent-inner')
if answer:
return str(answer)
else:
return None
def embed_images_in_base64(html_content):
soup = BeautifulSoup(html_content, 'html.parser')
images = soup.find_all('img')
prev_image_src = None
for img in images:
image_url = None
if 'data-actualsrc' in img.attrs:
image_url = img['data-actualsrc']
elif 'src' in img.attrs:
image_url = img['src']
if not image_url or image_url.startswith('data:image'):
continue
# 如果相邻的图像具有相同的src属性，则删除一个
if prev_image_src == image_url:
img.extract()
continue
response = requests.get(image_url)
response.raise_for_status()
image_data = response.content
image_ext = imghdr.what(None, image_data)
if not image_ext:
print(f'未知的图片格式: {image_url}')
continue
base64_encoded_image = base64.b64encode(image_data).decode('utf-8')
data_uri = f'data:image/{image_ext};base64,{base64_encoded_image}'
img['src'] = data_uri
prev_image_src = image_url
return str(soup)
def save_answer_to_html(answer_content, file_path):
html_template = '''
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>知乎答案</title>
<style>
body {
{
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol';
font-size: 16px;
line-height: 1.6;
color: #333;
max-width: 800px;
margin: 0 auto;
padding: 20px;
}}
img {
{
max-width: 100%;
height: auto;
}}
</style>
</head>
<body>
{content}
</body>
</html>
'''
with open(file_path, 'w', encoding='utf-8') as f:
f.write(html_template.format(content=answer_content))
def main(save_dir=None):
print("请输入知乎问题/答案的URL：")
zhihu_answer_url = input()
print("请输入输出文件的路径（按Enter默认当前工作路径）：")
save_dir = input()
if not save_dir.strip():
save_dir = os.getcwd() # 默认当前工作路径
else:
save_dir = os.path.abspath(save_dir) # 它会将相对路径转换为绝对路径，以便程序可以正确找到文件或目录。
# 无论用户输入相对路径还是绝对路径，程序都能正确地输出HTML文件到指定的位置。
# 将最终下载的内容保存到outputfile文件夹中
save_dir = os.path.join(save_dir, 'outputfile')
# 确保 outputfile 文件夹存在，如果不存在则创建
if not os.path.exists(save_dir):
os.makedirs(save_dir)
# 获取答案的HTML内容
html_content = fetch_url_content(zhihu_answer_url)
if not html_content:
print("无法获取答案HTML内容")
return
# 提取答案中的文字和图片
answer_content = extract_answer_content(html_content)
if not answer_content:
print("无法提取答案内容")
return
# 将图片转换为Base64并嵌入到答案内容中
answer_content_with_embedded_images = embed_images_in_base64(answer_content)
# 将答案内容保存为HTML文件
if not os.path.exists(save_dir):
os.makedirs(save_dir)
html_file_path = os.path.join(save_dir, 'answer.html')
save_answer_to_html(answer_content_with_embedded_images, html_file_path)
print(f"答案已保存到: {html_file_path}")
# 下载完成后，并打开
# output_file_path = os.path.join(save_dir, 'answer.html') # 具体可能需要替换
# webbrowser.open(output_file_path)
if __name__ == "__main__":
main()
os.system('pause') # 按任意键继续。
When the picture cannot be loaded, use the compatibility mode ie browser
exe file extraction
If you don't want to run the code, you can directly use the packaged exe file for processing
Link: https://pan.baidu.com/s/1K6rodH5iXUHdUf_PyB_1mg?pwd=75ec
Extraction code: 75ec