scrapling 0.2.96__py3-none-any.whl → 0.2.98__py3-none-any.whl

scrapling/parser.py

@@ -17,7 +17,7 @@ from scrapling.core.custom_types import (AttributesHandler, TextHandler,
 from scrapling.core.mixins import SelectorsGeneration
 from scrapling.core.storage_adaptors import (SQLiteStorageSystem,
                                              StorageSystemMixin, _StorageTools)
-from scrapling.core.translator import HTMLTranslator
+from scrapling.core.translator import translator_instance
 from scrapling.core.utils import (clean_spaces, flatten, html_forbidden,
                                   is_jsonable, log)
 
@@ -26,7 +26,7 @@ class Adaptor(SelectorsGeneration):
     __slots__ = (
         'url', 'encoding', '__auto_match_enabled', '_root', '_storage',
         '__keep_comments', '__huge_tree_enabled', '__attributes', '__text', '__tag',
-        '__keep_cdata', '__raw_body'
+        '__keep_cdata'
     )
 
     def __init__(
@@ -71,21 +71,18 @@ class Adaptor(SelectorsGeneration):
         if root is None and not body and text is None:
             raise ValueError("Adaptor class needs text, body, or root arguments to work")
 
-        self.__text = None
-        self.__raw_body = ''
+        self.__text = ''
         if root is None:
             if text is None:
                 if not body or not isinstance(body, bytes):
                     raise TypeError(f"body argument must be valid and of type bytes, got {body.__class__}")
 
                 body = body.replace(b"\x00", b"").strip()
-                self.__raw_body = body.replace(b"\x00", b"").strip().decode()
             else:
                 if not isinstance(text, str):
                     raise TypeError(f"text argument must be of type str, got {text.__class__}")
 
                 body = text.strip().replace("\x00", "").encode(encoding) or b"<html/>"
-                self.__raw_body = text.strip()
 
             # https://lxml.de/api/lxml.etree.HTMLParser-class.html
             parser = html.HTMLParser(
@@ -250,10 +247,7 @@ class Adaptor(SelectorsGeneration):
         """Return the inner html code of the element"""
         return TextHandler(etree.tostring(self._root, encoding='unicode', method='html', with_tail=False))
 
-    @property
-    def body(self) -> TextHandler:
-        """Return raw HTML code of the element/page without any processing when possible or return `Adaptor.html_content`"""
-        return TextHandler(self.__raw_body) or self.html_content
+    body = html_content
 
     def prettify(self) -> TextHandler:
         """Return a prettified version of the element's inner html-code"""
@@ -476,7 +470,7 @@ class Adaptor(SelectorsGeneration):
         try:
             if not self.__auto_match_enabled or ',' not in selector:
                 # No need to split selectors in this case, let's save some CPU cycles :)
-                xpath_selector = HTMLTranslator().css_to_xpath(selector)
+                xpath_selector = translator_instance.css_to_xpath(selector)
                 return self.xpath(xpath_selector, identifier or selector, auto_match, auto_save, percentage)
 
             results = []
@@ -484,7 +478,7 @@ class Adaptor(SelectorsGeneration):
                 for single_selector in split_selectors(selector):
                     # I'm doing this only so the `save` function save data correctly for combined selectors
                     # Like using the ',' to combine two different selectors that point to different elements.
-                    xpath_selector = HTMLTranslator().css_to_xpath(single_selector.canonical())
+                    xpath_selector = translator_instance.css_to_xpath(single_selector.canonical())
                     results += self.xpath(
                         xpath_selector, identifier or single_selector.canonical(), auto_match, auto_save, percentage
                     )

{scrapling-0.2.96.dist-info → scrapling-0.2.98.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: scrapling
-Version: 0.2.96
+Version: 0.2.98
 Summary: Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy again! In an internet filled with complications,
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair
@@ -73,6 +73,22 @@ Scrapling is a high-performance, intelligent web scraping library for Python tha
 
 # Sponsors 
 
+[Scrapeless Deep SerpApi](https://www.scrapeless.com/en/product/deep-serp-api?utm_source=website&utm_medium=ads&utm_campaign=scraping&utm_term=d4vinci) From $0.10 per 1,000 queries with a 1-2 second response time! 
+
+Deep SerpApi is a dedicated search engine designed for large language models (LLMs) and AI agents, aiming to provide real-time, accurate and unbiased information to help AI applications retrieve and process data efficiently.
+- covering 20+ Google SERP scenarios and mainstream search engines.
+- support real-time data updates to ensure real-time and accurate information.
+- It can integrate information from all available online channels and search engines.
+- Deep SerpApi will simplify the process of integrating dynamic web information into AI solutions, and ultimately achieve an ALL-in-One API for one-click search and extraction of web data.
+- **Developer Support Program**: Integrate Scrapeless Deep SerpApi into your AI tools, applications or projects. [We already support Dify, and will soon support frameworks such as Langchain, Langflow, FlowiseAI]. Then share your results on GitHub or social media, and you will get a 1-12 month free developer support opportunity, up to 500 free usage per month.
+- 🚀 **Scraping API**: Effortless and highly customizable data extraction with a single API call, providing structured data from any website.
+- ⚡ **Scraping Browser**: AI-powered and LLM-driven, it simulates human-like behavior with genuine fingerprints and headless browser support, ensuring seamless, block-free scraping.
+- 🌐 **Proxies**: Use high-quality, rotating proxies to scrape top platforms like Amazon, Shopee, and more, with global coverage in 195+ countries.
+
+
+[![Scrapeless Banner](https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/scrapeless.jpg)](https://www.scrapeless.com/en/product/deep-serp-api?utm_source=website&utm_medium=ads&utm_campaign=scraping&utm_term=d4vinci)
+---
+
 [Evomi](https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling) is your Swiss Quality Proxy Provider, starting at **$0.49/GB**
 
 - 👩‍💻 **$0.49 per GB Residential Proxies**: Our price is unbeatable
@@ -88,21 +104,6 @@ Scrapling is a high-performance, intelligent web scraping library for Python tha
 [![Evomi Banner](https://my.evomi.com/images/brand/cta.png)](https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling)
 ---
 
-[Scrapeless](https://www.scrapeless.com/?utm_source=github&utm_medium=ads&utm_campaign=scraping&utm_term=D4Vinci) is your all-in-one web scraping toolkit, starting at just $0.60 per 1k URLs!
-
-- 🚀 Scraping API: Effortless and highly customizable data extraction with a single API call, providing structured data from any website.
-- ⚡ Scraping Browser: AI-powered and LLM-driven, it simulates human-like behavior with genuine fingerprints and headless browser support, ensuring seamless, block-free scraping.
-- 🔒 Web Unlocker: Bypass CAPTCHAs, IP blocks, and dynamic content in real time, ensuring uninterrupted access.
-- 🌐 Proxies: Use high-quality, rotating proxies to scrape top platforms like Amazon, Shopee, and more, with global coverage in 195+ countries.
-- 💼 Enterprise-Grade: Custom solutions for large-scale and complex data needs.
-- 🎁 Free Trial: Try before you buy—experience our service firsthand.
-- 💬 Pay-Per-Use: Flexible, cost-effective pricing with no long-term commitments.
-- 🔧 Easy Integration: Seamlessly integrate with your existing tools and workflows for hassle-free automation.
-
-
-[![Scrapeless Banner](https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/scrapeless.jpg)](https://www.scrapeless.com/?utm_source=github&utm_medium=ads&utm_campaign=scraping&utm_term=D4Vinci)
----
-
 ## Table of content
   * [Key Features](#key-features)
     * [Fetch websites as you prefer](#fetch-websites-as-you-prefer-with-async-support)
@@ -172,7 +173,7 @@ Scrapling is a high-performance, intelligent web scraping library for Python tha
 ## Getting Started
 
 ```python
-from scrapling import Fetcher
+from scrapling.fetchers import Fetcher
 
 fetcher = Fetcher(auto_match=False)
 
@@ -254,7 +255,7 @@ Fetchers are interfaces built on top of other libraries with added features that
 ### Features
 You might be slightly confused by now so let me clear things up. All fetcher-type classes are imported in the same way
 ```python
-from scrapling import Fetcher, StealthyFetcher, PlayWrightFetcher
+from scrapling.fetchers import Fetcher, StealthyFetcher, PlayWrightFetcher
 ```
 All of them can take these initialization arguments: `auto_match`, `huge_tree`, `keep_comments`, `keep_cdata`, `storage`, and `storage_args`, which are the same ones you give to the `Adaptor` class.
 
@@ -286,7 +287,7 @@ You can route all traffic (HTTP and HTTPS) to a proxy for any of these methods i
 ```
 For Async requests, you will just replace the import like below:
 ```python
->> from scrapling import AsyncFetcher
+>> from scrapling.fetchers import AsyncFetcher
 >> page = await AsyncFetcher().get('https://httpbin.org/get', stealthy_headers=True, follow_redirects=True)
 >> page = await AsyncFetcher().post('https://httpbin.org/post', data={'key': 'value'}, proxy='http://username:password@localhost:8030')
 >> page = await AsyncFetcher().put('https://httpbin.org/put', data={'key': 'value'})
@@ -540,7 +541,7 @@ When website owners implement structural changes like
 The selector will no longer function and your code needs maintenance. That's where Scrapling's auto-matching feature comes into play.
 
 ```python
-from scrapling import Adaptor
+from scrapling.parser import Adaptor
 # Before the change
 page = Adaptor(page_source, url='example.com')
 element = page.css('#p1' auto_save=True)
@@ -558,7 +559,7 @@ To solve this issue, I will use [The Web Archive](https://archive.org/)'s [Wayba
 If I want to extract the Questions button from the old design I can use a selector like this `#hmenus > div:nth-child(1) > ul > li:nth-child(1) > a` This selector is too specific because it was generated by Google Chrome.
 Now let's test the same selector in both versions
 ```python
->> from scrapling import Fetcher
+>> from scrapling.fetchers import Fetcher
 >> selector = '#hmenus > div:nth-child(1) > ul > li:nth-child(1) > a'
 >> old_url = "https://web.archive.org/web/20100102003420/http://stackoverflow.com/"
 >> new_url = "https://stackoverflow.com/"
@@ -619,7 +620,7 @@ Note: The filtering process always starts from the first filter it finds in the
 Examples to clear any confusion :)
 
 ```python
->> from scrapling import Fetcher
+>> from scrapling.fetchers import Fetcher
 >> page = Fetcher().get('https://quotes.toscrape.com/')
 # Find all elements with tag name `div`.
 >> page.find_all('div')

{scrapling-0.2.96.dist-info → scrapling-0.2.98.dist-info}/RECORD

@@ -1,25 +1,25 @@
-scrapling/__init__.py,sha256=5r6_yxrfXbeoh8UqUaCdmmbWH9TQxBivP9cLWUXPI5g,500
+scrapling/__init__.py,sha256=S-SWj9O2r0Tu8Z-mPxDJ-z3h5k-bBfhFOETaCY4A9dc,1510
 scrapling/cli.py,sha256=7yTsMhVAqqS8Z27T5dFKrR9_X8vuFjBlwYgAF22W7T8,1292
-scrapling/defaults.py,sha256=sdXeZjXEX7PmCtaa0weK0nRrAUzqZukNNqipZ_sltYE,469
-scrapling/fetchers.py,sha256=qmiJ6S-bnPWvP48Z6rKxBnSuR-tdwHlJwlIsYxGxFM0,35405
-scrapling/parser.py,sha256=b_1eHxRwHRCidyvm3F6ST6qIYvVEVU6GhTTCI1LblVk,54330
+scrapling/defaults.py,sha256=MAn2MMLBFvoe4i3u_qlp6YEvGUiCjNPPDux1cFCdpsU,866
+scrapling/fetchers.py,sha256=xwVCjAg0VCXwhB2igSLQvb0D0bOPGfg5WNtxgE7m-W0,34987
+scrapling/parser.py,sha256=1xS1UjCm1GVnKcVAtup9rSE1xuYPxXOgJe-8LJE5gUk,53956
 scrapling/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
 scrapling/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 scrapling/core/_types.py,sha256=dKVi_dUxdxNtTr7sj7ySkHXDfrsmjFTfpCQeO5tGuBY,670
-scrapling/core/custom_types.py,sha256=tejeLYmWa_aLaLtMSymG4z7h6rxO-9EvmiRWEWcW54s,13022
+scrapling/core/custom_types.py,sha256=EWGx5t5scHEB1SMsitzc8duskq-5f-Qaj40IWkNTRzM,12947
 scrapling/core/mixins.py,sha256=sozbpaGL1_O_x3U-ABM5aYWpnxpCLfdbcA9SG3P7weY,3532
-scrapling/core/storage_adaptors.py,sha256=l_ZYcdn1y69AcoPuRrPoaxqKysN62pMExrwJWYdu5MA,6220
-scrapling/core/translator.py,sha256=hFSc3mxG5pYhbwRgingeFbD_E73U799vCsvVv0uFEXw,5237
-scrapling/core/utils.py,sha256=03LzCDzmeK1TXPjIKVzHSUgSfhpe36XE8AwxlgxzJoU,3705
+scrapling/core/storage_adaptors.py,sha256=gZbUpHtLOL7o_oZbES_o40r39zShxTeTM8YK6dXA5Zo,6214
+scrapling/core/translator.py,sha256=3a2VX9KR-q-GzwT1OgGDv1UlzIkvBggkQXUdiMyL-4c,5277
+scrapling/core/utils.py,sha256=KX88B3tV1-SgCAr69TUN3LfmsTDcLnEhYJiPuWd31yA,3704
 scrapling/engines/__init__.py,sha256=zA7tzqcDXP0hllwmjVewNHWipIA4JSU9mRG4J-cud0c,267
-scrapling/engines/camo.py,sha256=SHMRnIrN6599upo5-G3fZQ10455xyB-bB_EsLMjBStA,16072
+scrapling/engines/camo.py,sha256=oYKA0l3EpOcQW2APRj5FEmslqtp9A8i_ZljqlKvIDeI,16129
 scrapling/engines/constants.py,sha256=Gb_nXFoBB4ujJkd05SKkenMe1UDiRYQA3dkmA3DunLg,3723
-scrapling/engines/pw.py,sha256=LvS1jvTf3s7mfdeQo7_OyQ5zpiOzvBu5g88hOLlQBCQ,20856
-scrapling/engines/static.py,sha256=8v6RmdsSP6fAtWNXaJG24evHPsZ2oDiBl7yfkLrdARU,10635
+scrapling/engines/pw.py,sha256=cZraIBWd9ulEGEdhETIGmpevi62CN9JGcUU1OIDdxkA,21369
+scrapling/engines/static.py,sha256=EjdaR0beqWfEKKavT7vlBnozoayQaVpqeVtaOuzd384,9306
 scrapling/engines/toolbelt/__init__.py,sha256=VQDdYm1zY9Apno6d8UrULk29vUjllZrQqD8mXL1E2Fc,402
-scrapling/engines/toolbelt/custom.py,sha256=qgONLwpxUoEIAIQBF1RcakYu8cqAAmX8qdyaol5hfjA,12813
-scrapling/engines/toolbelt/fingerprints.py,sha256=ajEHdXHr7W4hw9KcNS7XlyxNBZu37p1bRj18TiICLzU,2929
-scrapling/engines/toolbelt/navigation.py,sha256=xEfZRJefuxOCGxQOSI2llS0du0Y2XmoIPdVGUSHOd7k,4567
+scrapling/engines/toolbelt/custom.py,sha256=_-baGB8oOOHogbaddtGsq_K_01ccOjOkGA6tOKk28hM,12811
+scrapling/engines/toolbelt/fingerprints.py,sha256=Zzoqq3p6X_8D7eTxACz3z96cBZWWK61iKOGo2sZUtlg,2924
+scrapling/engines/toolbelt/navigation.py,sha256=fMjDgicqy2MoZZll2h5EvrrxkL6yNrC09v8isTpwAt0,4565
 scrapling/engines/toolbelt/bypasses/navigator_plugins.js,sha256=tbnnk3nCXB6QEQnOhDlu3n-s7lnUTAkrUsjP6FDQIQg,2104
 scrapling/engines/toolbelt/bypasses/notification_permission.js,sha256=poPM3o5WYgEX-EdiUfDCllpWfc3Umvw4jr2u6O6elus,237
 scrapling/engines/toolbelt/bypasses/pdf_viewer.js,sha256=mKjjSuP1-BOGC_2WhRYHJo_LP7lTBi2KXmP_zsHO_tI,173
@@ -41,9 +41,9 @@ tests/fetchers/sync/test_playwright.py,sha256=MEyDRaMyxDIWupG7f_xz0f0jd9Cpbd5rXC
 tests/parser/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/parser/test_automatch.py,sha256=SxsNdExE8zz8AcPRQFBUjZ3Q_1-tPOd9dzVvMSZpOYQ,4908
 tests/parser/test_general.py,sha256=dyfOsc8lleoY4AxcfDUBUaD1i95xecfYuTUhKBsYjwo,12100
-scrapling-0.2.96.dist-info/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
-scrapling-0.2.96.dist-info/METADATA,sha256=yNRmjMR5qmJyH_6ob-6nwLuqD6iXIegMI-d-xQ95ZpA,69063
-scrapling-0.2.96.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-scrapling-0.2.96.dist-info/entry_points.txt,sha256=DHyt2Blxy0P5OE2HRcP95Wz9_xo2ERCDcNqrJjYS3o8,49
-scrapling-0.2.96.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
-scrapling-0.2.96.dist-info/RECORD,,
+scrapling-0.2.98.dist-info/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
+scrapling-0.2.98.dist-info/METADATA,sha256=Un_ROxrGIvk_8w-ECQbwKAcJzYyx3MTWS1DHt9FRqdI,69718
+scrapling-0.2.98.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+scrapling-0.2.98.dist-info/entry_points.txt,sha256=DHyt2Blxy0P5OE2HRcP95Wz9_xo2ERCDcNqrJjYS3o8,49
+scrapling-0.2.98.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
+scrapling-0.2.98.dist-info/RECORD,,

{scrapling-0.2.96.dist-info → scrapling-0.2.98.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.2)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any