Ignore JS references to img and tidy up long lines. (e7bb66db) · Commits · The Heavy / imgslipstream

imgslipstream.py

+37 −11

Original line number	Diff line number	Diff line
		@@ -30,7 +30,8 @@ if __name__ == '__main__':
		p.add_argument('source')
		p.add_argument('--verbose', '-v', action='store_true', help='Print more logging to the console.')
		p.add_argument('--files', '-f', action='store_true', help='Make local files instead of embedding.')
		p.add_argument('--maxlen', '-m', action='store', help='Change the max length of URLs allowed (default 100).', default=100, type=int)
		p.add_argument('--maxlen', '-m', action='store', help='Change the max length of URLs allowed (default 100).',
		default=100, type=int)
		args = p.parse_args()
		log.info('Arguments: %s', args)

		@@ -75,14 +76,18 @@ if __name__ == '__main__':
		elif document[img_tag - 4:img_tag] == '<':
		img_end_tag = document.find('>', img_tag)
		log.debug('img_end_tag = {0}'.format(img_end_tag))
		elif document[img_tag:img_tag + 5] == 'img {' or document[img_tag - 1:img_tag + 4] == ',img,':
		log.debug('Quietly skipping a CSS tag.')
		elif document[img_tag:img_tag + 5] == 'img {' or document[img_tag - 1:img_tag + 4] == ',img,' \
		or document[img_tag - 1:img_tag + 4] == '\|img\|':
		log.debug('Quietly skipping a CSS or JS reference to an img tag.')
		continue
		elif document[img_tag - 2:img_tag + 9] == 'i.imgur.com' or document[img_tag - 6:img_tag + 6] == 'i.postimg.cc':
		elif document[img_tag - 2:img_tag + 9] == 'i.imgur.com' \
		or document[img_tag - 6:img_tag + 6] == 'i.postimg.cc':
		log.debug('Quietly skipping a domain with img in it (not an img tag).')
		continue
		else:
		log.warning('img keyword found without < or <, skipped: {0}'.format(document[img_tag - 4:img_tag + 40]))
		log.warning(
		'img keyword found without < or <, skipped: {0}'.format(document[img_tag - 4:img_tag + 40])
		)
		continue

		src_attr = document.find('src', img_tag, img_end_tag)
		@@ -103,15 +108,27 @@ if __name__ == '__main__':
		log.debug('using last resort (src + 3) src_quote = {0}'.format(src_quote))
		src_end_quote = document.find(' ', src_quote + 1)
		src_quote_type = ''
		log.debug('using alternate ( ) src_end_quote = {0}, src_quote_type = {1}'.format(src_end_quote, src_quote_type))
		log.debug(
		'using alternate ( ) src_end_quote = {0}, src_quote_type = {1}'.format(
		src_end_quote, src_quote_type
		)
		)
		else:
		src_end_quote = document.find('"', src_quote + 6, img_end_tag)
		src_quote_type = '"'
		log.debug('using alternate (") src_end_quote = {0}, src_quote_type = {1}'.format(src_end_quote, src_quote_type))
		log.debug(
		'using alternate (") src_end_quote = {0}, src_quote_type = {1}'.format(
		src_end_quote, src_quote_type
		)
		)
		else:
		src_end_quote = document.find('"', src_quote + 1, img_end_tag)
		src_quote_type = '"'
		log.debug('using main (") src_end_quote = {0}, src_quote_type = {1}'.format(src_end_quote, src_quote_type))
		log.debug(
		'using main (") src_end_quote = {0}, src_quote_type = {1}'.format(
		src_end_quote, src_quote_type
		)
		)
		url = document[src_quote + 1:src_end_quote].strip()
		log.debug('url = {0}'.format(url))
		if len(url) < 5:
		@@ -124,7 +141,11 @@ if __name__ == '__main__':
		log.warning('src attribute not http: {0}'.format(document[img_tag - 4:img_end_tag + 40]))
		continue
		if len(url) > args.maxlen:
		log.warning('src attribute too long (use -m if required): {0}'.format(document[img_tag - 4:img_tag + args.maxlen]))
		log.warning(
		'src attribute too long (use -m if required): {0}'.format(
		document[img_tag - 4:img_tag + args.maxlen]
		)
		)
		continue
		if '.' not in url:
		log.warning('Invalid URL, no dots (.) found: {0}'.format(document[img_tag - 4:img_end_tag + 40]))
		@@ -139,7 +160,11 @@ if __name__ == '__main__':
		req = requests.get(url)
		log.debug('req = {0} {1}'.format(req.status_code, req.reason))
		if req.status_code != 200:
		log.warning('{1} {2}: {0}'.format(document[img_tag - 4:img_end_tag + 40], req.status_code, req.reason))
		log.warning(
		'{1} {2}: {0}'.format(
		document[img_tag - 4:img_end_tag + 40], req.status_code, req.reason
		)
		)
		continue
		orig = document[src_attr:src_end_quote + len(src_quote_type)]
		count = document.count(orig)
		@@ -151,7 +176,8 @@ if __name__ == '__main__':
		replacement = 'src=' + src_quote_type + dest_folder.name + '/' + dest_file.name + src_quote_type
		log.debug('replacement = {0}'.format(replacement))
		else:
		replacement = 'src=' + src_quote_type + 'data:image/' + file_type + ';base64,' + base64.b64encode(req.content).decode() + src_quote_type
		replacement = 'src=' + src_quote_type + 'data:image/' + file_type + ';base64,' + \
		base64.b64encode(req.content).decode() + src_quote_type
		log.debug('replacement[:40]...[-10:] = {0}...{1}'.format(replacement[:40], replacement[-10:]))
		document = document.replace(orig, replacement)
		log.info('Replaced {0} instances of: {1}'.format(count, orig))