Last active
October 5, 2025 06:57
-
-
Save eriksachse/ca188cd885dce195e1e473c21360835e to your computer and use it in GitHub Desktop.
This file contains hidden or 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 html.parser import HTMLParser | |
| class ImageParser(HTMLParser): | |
| def __init__(self): | |
| super().__init__() | |
| self.image_rows = [] # list of [url, caption] | |
| self.current_img = None | |
| self.in_caption_div = False | |
| self.in_caption_p = False | |
| self.current_caption = '' | |
| def handle_starttag(self, tag, attrs): | |
| attr_dict = dict(attrs) | |
| # check if we entered a wp-caption div | |
| if tag == "div" and 'class' in attr_dict and 'wp-caption' in attr_dict['class']: | |
| self.in_caption_div = True | |
| self.current_img = None | |
| self.current_caption = '' | |
| # image inside wp-caption | |
| if self.in_caption_div and tag == "img": | |
| src = attr_dict.get('src', '') | |
| if src.endswith('.svg') or 'Searchtool' in src: | |
| return | |
| width = int(attr_dict.get('width', 0)) | |
| height = int(attr_dict.get('height', 0)) | |
| if width and height and (width < 50 or height < 50): | |
| return | |
| self.current_img = src | |
| # paragraph for caption text | |
| if self.in_caption_div and tag == "p" and 'class' in attr_dict and 'wp-caption-text' in attr_dict['class']: | |
| self.in_caption_p = True | |
| self.current_caption = '' | |
| def handle_endtag(self, tag): | |
| # leave caption paragraph | |
| if tag == "p" and self.in_caption_p: | |
| self.in_caption_p = False | |
| # leave wp-caption div | |
| if tag == "div" and self.in_caption_div: | |
| if self.current_img: # store row [img, caption] | |
| self.image_rows.append([self.current_img, self.current_caption.strip()]) | |
| self.in_caption_div = False | |
| self.current_img = None | |
| self.current_caption = '' | |
| def handle_data(self, data): | |
| if self.in_caption_p: | |
| self.current_caption += data | |
| def onResponse(webClientDAT, statusCode, headerDict, data, id): | |
| encoding = headerDict.get('content-type', '') | |
| encoding = encoding.split('charset=')[-1] if 'charset=' in encoding else 'utf-8' | |
| html = data.decode(encoding) | |
| parser = ImageParser() | |
| parser.feed(html) | |
| table = op('image_urls') | |
| table.clear() | |
| # write URL + caption to table | |
| for row in parser.image_rows: | |
| table.appendRow(row) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment