Last active
September 12, 2023 13:58
-
-
Save 0scarB/ed330536fd098ccdca9b7a8b09d9d4a0 to your computer and use it in GitHub Desktop.
Quick and dirty function to extract image URLs from 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
| from collections.abc import Iterable | |
| import urllib | |
| def find_image_urls_in_markdown(s: str) -> Iterable[str]: | |
| context = "" | |
| alt_text_chars = [] | |
| url_chars = [] | |
| for char in s: | |
| if context == "": | |
| if char == "!": | |
| context = "after_exclamation" | |
| elif context == "after_exclamation": | |
| if char == "[": | |
| context = "alt_text" | |
| elif context == "alt_text": | |
| if char == "]": | |
| context = "alt_text_end" | |
| else: | |
| alt_text_chars.append(char) | |
| elif context == "alt_text_end": | |
| if char == "(": | |
| context = "url" | |
| else: | |
| alt_text_chars.clear() | |
| context = "" | |
| elif context == "url": | |
| if char == ")": | |
| yield from find_image_urls_in_markdown("".join(alt_text_chars)) | |
| yield "".join(url_chars).strip() | |
| # Use next line instead to escape special chars | |
| #yield urllib.parse.quote("".join(url_chars).strip().encode('utf-8'), safe="/:") | |
| alt_text_chars.clear() | |
| url_chars.clear() | |
| context = "" | |
| else: | |
| url_chars.append(char) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment