Last active
August 14, 2024 19:02
-
-
Save AlmogBaku/baffe45fed8188a28c6238806ae6ae58 to your computer and use it in GitHub Desktop.
Medium to Markdown
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import mimetypes | |
import os | |
import markdownify | |
import requests | |
mimetypes.init() | |
class MediumConverter(markdownify.MarkdownConverter): | |
def convert_figure(self, el, text, convert_as_inline): | |
img_element = el.find('img') | |
caption_element = el.find('figcaption') | |
if img_element: | |
src = img_element.attrs.get('src', None) or el.select_one('source').attrs['srcset'].split()[0] | |
caption = caption_element.get_text(strip=True) if caption_element else '' | |
alt = (img_element.attrs.get('alt', None) or | |
img_element.attrs.get('title', None) or | |
(caption_element.get_text(strip=True) if caption_element else '')) | |
if src: | |
return f'![{alt}]({src})\n*{caption}*' if caption else f'![{alt}]({src})' | |
return '' | |
def convert_soup(self, soup): | |
section = soup.select_one('section') | |
ignored = section.select('.speechify-ignore') | |
for i in ignored: | |
i.decompose() | |
hr = section.select('div[role="separator"]') | |
for i in hr: | |
# replace with hr tag | |
i.replace_with(soup.new_tag('hr')) | |
if self.save: | |
if not self.name: | |
self.name = ( | |
soup.select_one('title') | |
.get_text(strip=True) | |
.split('|')[0].strip() | |
.replace(' ', '_', -1).replace(':', '_', -1) | |
.replace('?', '', -1).replace('!', '', -1) | |
.replace('’', '', 1).replace('‘', '', -1) | |
.replace('“', '', -1).replace('”', '', -1) | |
) | |
if self.name: | |
self.base_save_path += self.name + '/' | |
os.makedirs(self.base_save_path, exist_ok=True) | |
converted = super().convert_soup(section) | |
if self.save: | |
filename = 'output.md' | |
with open(f"{self.base_save_path}{filename}", 'w', encoding='utf-8') as f: | |
f.write(converted) | |
print(f'Document saved as {self.base_save_path}{filename}') | |
return converted | |
image_i = 0 | |
def convert_img(self, el, text, convert_as_inline): | |
if self.save: | |
src = el.get('src') | |
if not src: | |
src = el.parent.select('source')[-1].get('srcset').split()[0] | |
img_resp = requests.get(src) | |
ext = mimetypes.guess_extension(img_resp.headers['Content-Type']) | |
filename = f"{self.image_i}{ext}" | |
self.image_i += 1 | |
with open(f"{self.base_save_path}{filename}", 'wb') as f: | |
f.write(img_resp.content) | |
print(f'Image saved as {self.base_save_path}{filename}') | |
el.attrs['src'] = filename | |
return super().convert_img(el, text, convert_as_inline) | |
def __init__(self, save=False, name=None, *args, **kwargs): | |
self.save = save | |
self.name = name | |
if save: | |
self.base_save_path = 'out/' | |
os.makedirs(self.base_save_path, exist_ok=True) | |
super().__init__(heading_style=markdownify.ATX, *args, **kwargs) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment