From 288333cadd636e99a58dc478ff27239f8750a67e Mon Sep 17 00:00:00 2001 From: Tristan Lee Date: Sun, 25 Dec 2022 13:53:08 -0800 Subject: [PATCH] added edge cases support for url regex --- app.py | 6 +----- cisticola/base.py | 5 ++++- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/app.py b/app.py index 14f2ad6..1b25998 100644 --- a/app.py +++ b/app.py @@ -52,11 +52,7 @@ def get_transformer_controller(): controller = ETLController() controller.connect_to_db(engine) - transformers = [VkontakteTransformer(), - TelegramTelethonTransformer(), - GettrTransformer(), - BitchuteTransformer(), - RumbleTransformer()] + transformers = [TelegramTelethonTransformer(),] controller.register_transformers(transformers) diff --git a/cisticola/base.py b/cisticola/base.py index 26c9bfa..322c18f 100644 --- a/cisticola/base.py +++ b/cisticola/base.py @@ -263,8 +263,11 @@ class Post: def hydrate(self): URL_REGEX = r"""(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:\'\".,<>?«»“”‘’])|(?:(?