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 `css_first` and `xpath_first` for easier usage

Karim shoair362204044098
diff --git a/README.md b/README.md
index 8ac4e06..84e6ada 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,7 @@ quotes = page.css('.quote').css('.text::text') # Chained selectors
quotes = [element.text for element in page.css('.quote').css('.text')] # Slower than bulk query above
# Get the first quote element
-quote = page.css('.quote').first # or [0] or .get()
+quote = page.css_first('.quote') # or page.css('.quote').first or [0] or .get()
# Working with elements
quote.html_content # Inner HTML
@@ -244,8 +244,8 @@ To increase the complexity a little bit, let's say we want to get all books' dat
```python
>>> for product in page.find_by_text('Tipping the Velvet').parent.parent.find_similar():
print({
- "name": product.css('h3 a::text')[0],
- "price": product.css('.price_color')[0].re_first(r'[\d\.]+'),
+ "name": product.css_first('h3 a::text'),
+ "price": product.css_first('.price_color').re_first(r'[\d\.]+'),
"stock": product.css('.availability::text')[-1].clean()
})
{'name': 'A Light in the ...', 'price': '51.77', 'stock': 'In stock'}
diff --git a/scrapling/parser.py b/scrapling/parser.py
index 3416ec6..4f994b4 100644
--- a/scrapling/parser.py
+++ b/scrapling/parser.py
@@ -394,6 +394,58 @@ class Adaptor(SelectorsGeneration):
return self.__convert_results(score_table[highest_probability])
return []
+ def css_first(self, selector: str, identifier: str = '',
+ auto_match: bool = False, auto_save: bool = False, percentage: int = 0
+ ) -> Union['Adaptors[Adaptor]', List, None]:
+ """Search current tree with CSS3 selectors and return the first result if possible, otherwise return `None`
+
+ **Important:
+ It's recommended to use the identifier argument if you plan to use different selector later
+ and want to relocate the same element(s)**
+
+ :param selector: The CSS3 selector to be used.
+ :param auto_match: Enabled will make function try to relocate the element if it was 'saved' before
+ :param identifier: A string that will be used to save/retrieve element's data in auto-matching
+ otherwise the selector will be used.
+ :param auto_save: Automatically save new elements for `auto_match` later
+ :param percentage: The minimum percentage to accept while auto-matching and not going lower than that.
+ Be aware that the percentage calculation depends solely on the page structure so don't play with this
+ number unless you must know what you are doing!
+
+ :return: List as :class:`Adaptors`
+ """
+ try:
+ return self.css(selector, identifier, auto_match, auto_save, percentage)[0]
+ except (IndexError, TypeError,):
+ return None
+
+ def xpath_first(self, selector: str, identifier: str = '',
+ auto_match: bool = False, auto_save: bool = False, percentage: int = 0, **kwargs: Any
+ ) -> Union['Adaptors[Adaptor]', List, None]:
+ """Search current tree with XPath selectors and return the first result if possible, otherwise return `None`
+
+ **Important:
+ It's recommended to use the identifier argument if you plan to use different selector later
+ and want to relocate the same element(s)**
+
+ Note: **Additional keyword arguments will be passed as XPath variables in the XPath expression!**
+
+ :param selector: The XPath selector to be used.
+ :param auto_match: Enabled will make function try to relocate the element if it was 'saved' before
+ :param identifier: A string that will be used to save/retrieve element's data in auto-matching
+ otherwise the selector will be used.
+ :param auto_save: Automatically save new elements for `auto_match` later
+ :param percentage: The minimum percentage to accept while auto-matching and not going lower than that.
+ Be aware that the percentage calculation depends solely on the page structure so don't play with this
+ number unless you must know what you are doing!
+
+ :return: List as :class:`Adaptors`
+ """
+ try:
+ return self.xpath(selector, identifier, auto_match, auto_save, percentage, **kwargs)[0]
+ except (IndexError, TypeError,):
+ return None
+
def css(self, selector: str, identifier: str = '',
auto_match: bool = False, auto_save: bool = False, percentage: int = 0
) -> Union['Adaptors[Adaptor]', List]: