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 empty methods (get/get_all/extract/extract_all)

Karim shoair45e86f50a37a
diff --git a/scrapling/core/custom_types.py b/scrapling/core/custom_types.py
index f952da7..0419406 100644
--- a/scrapling/core/custom_types.py
+++ b/scrapling/core/custom_types.py
@@ -89,6 +89,16 @@ class TextHandler(str):
data = re.sub(' +', ' ', data)
return self.__class__(data.strip())
+ # For easy copy-paste from Scrapy/parsel code when needed :)
+ def get(self, default=None):
+ return self
+
+ def get_all(self):
+ return self
+
+ extract = get_all
+ extract_first = get
+
def json(self) -> Dict:
"""Return json response if the response is jsonable otherwise throw error"""
# Using str function as a workaround for orjson issue with subclasses of str
@@ -186,6 +196,19 @@ class TextHandlers(List[TextHandler]):
return result
return default
+ # For easy copy-paste from Scrapy/parsel code when needed :)
+ def get(self, default=None):
+ """Returns the first item of the current list
+ :param default: the default value to return if the current list is empty
+ """
+ return self[0] if len(self) > 0 else default
+
+ def extract(self):
+ return self
+
+ extract_first = get
+ get_all = extract
+
class AttributesHandler(Mapping):
"""A read-only mapping to use instead of the standard dictionary for the speed boost but at the same time I use it to add more functionalities.
diff --git a/scrapling/parser.py b/scrapling/parser.py
index daaa8c4..169c9e7 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -330,6 +330,16 @@ class Adaptor(SelectorsGeneration):
return self.__convert_results(prev_element)
+ # For easy copy-paste from Scrapy/parsel code when needed :)
+ def get(self, default=None):
+ return self
+
+ def get_all(self):
+ return self
+
+ extract = get_all
+ extract_first = get
+
def __str__(self) -> str:
return self.html_content
@@ -1073,12 +1083,19 @@ class Adaptors(List[Adaptor]):
]
return self.__class__(results) if results else results
+ # For easy copy-paste from Scrapy/parsel code when needed :)
def get(self, default=None):
"""Returns the first item of the current list
:param default: the default value to return if the current list is empty
"""
return self[0] if len(self) > 0 else default
+ def extract(self):
+ return self
+
+ extract_first = get
+ get_all = extract
+
@property
def first(self):
"""Returns the first item of the current list or `None` if the list is empty"""