Skip to content

🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev

Adding `urljoin` method to Adaptors and Responses

Karim shoair5f9c3980dc5c
diff --git a/scrapling/parser.py b/scrapling/parser.py
index 169c9e7..85fd79e 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -2,6 +2,7 @@ import inspect
import os
import re
from difflib import SequenceMatcher
+from urllib.parse import urljoin
from cssselect import SelectorError, SelectorSyntaxError
from cssselect import parse as split_selectors
@@ -243,6 +244,10 @@ class Adaptor(SelectorsGeneration):
return TextHandler(separator.join([s for s in _all_strings]))
+ def urljoin(self, relative_url: str) -> str:
+ """Join this Adaptor's url with a relative url to form an absolute full URL."""
+ return urljoin(self.url, relative_url)
+
@property
def attrib(self) -> AttributesHandler:
"""Get attributes of the element"""