freedak/Scrapling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Handling an edge case and adding more commentary

Browse Source
This commit is contained in:
Karim shoair
2024-10-16 19:32:01 +03:00
parent a01cfe66db
commit d546b3499b
1 changed files with 14 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/parser.py
+4
View File
@@ -188,6 +188,7 @@ class Adaptor(SelectorsGeneration):
"""Get text content of the element""" """Get text content of the element"""
if not self.__text: if not self.__text:
if self.__keep_comments: if self.__keep_comments:
if not self.children:
# If use chose to keep comments, remove comments from text # If use chose to keep comments, remove comments from text
# Escape lxml default behaviour and remove comments like this `<span>CONDITION: <!-- -->Excellent</span>` # Escape lxml default behaviour and remove comments like this `<span>CONDITION: <!-- -->Excellent</span>`
# This issue is present in parsel/scrapy as well so no need to repeat it here so the user can run regex on the full text. # This issue is present in parsel/scrapy as well so no need to repeat it here so the user can run regex on the full text.
@@ -200,6 +201,9 @@ class Adaptor(SelectorsGeneration):
self.__text = TextHandler(fragment_root.text) self.__text = TextHandler(fragment_root.text)
else: else:
self.__text = TextHandler(self._root.text) self.__text = TextHandler(self._root.text)
else:
# If user already chose to not keep comments then all is good
self.__text = TextHandler(self._root.text)
return self.__text return self.__text
def get_all_text(self, separator: str = "\n", strip: bool = False, ignore_tags: Tuple = ('script', 'style',), valid_values: bool = True) -> TextHandler: def get_all_text(self, separator: str = "\n", strip: bool = False, ignore_tags: Tuple = ('script', 'style',), valid_values: bool = True) -> TextHandler: