scrapling 0.3__tar.gz → 0.3.2__tar.gz

{scrapling-0.3/scrapling.egg-info → scrapling-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapling
-Version: 0.3
+Version: 0.3.2
 Summary: Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair
@@ -64,23 +64,26 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: lxml>=6.0.0
+Requires-Dist: lxml>=6.0.1
 Requires-Dist: cssselect>=1.3.0
-Requires-Dist: click>=8.2.1
-Requires-Dist: orjson>=3.11.2
+Requires-Dist: orjson>=3.11.3
 Requires-Dist: tldextract>=5.3.0
-Requires-Dist: curl_cffi>=0.13.0
-Requires-Dist: playwright>=1.52.0
-Requires-Dist: rebrowser-playwright>=1.52.0
-Requires-Dist: camoufox>=0.4.11
-Requires-Dist: geoip2>=5.1.0
-Requires-Dist: msgspec>=0.19.0
+Provides-Extra: fetchers
+Requires-Dist: click>=8.2.1; extra == "fetchers"
+Requires-Dist: curl_cffi>=0.13.0; extra == "fetchers"
+Requires-Dist: playwright>=1.52.0; extra == "fetchers"
+Requires-Dist: rebrowser-playwright>=1.52.0; extra == "fetchers"
+Requires-Dist: camoufox>=0.4.11; extra == "fetchers"
+Requires-Dist: geoip2>=5.1.0; extra == "fetchers"
+Requires-Dist: msgspec>=0.19.0; extra == "fetchers"
 Provides-Extra: ai
-Requires-Dist: mcp>=1.13.0; extra == "ai"
+Requires-Dist: mcp>=1.14.0; extra == "ai"
 Requires-Dist: markdownify>=1.2.0; extra == "ai"
+Requires-Dist: scrapling[fetchers]; extra == "ai"
 Provides-Extra: shell
 Requires-Dist: IPython>=8.37; extra == "shell"
 Requires-Dist: markdownify>=1.2.0; extra == "shell"
+Requires-Dist: scrapling[fetchers]; extra == "shell"
 Provides-Extra: all
 Requires-Dist: scrapling[ai,shell]; extra == "all"
 Dynamic: license-file
@@ -155,9 +158,10 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 <!-- sponsors -->
 
 <a href="https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling" target="_blank" title="Evomi is your Swiss Quality Proxy Provider, starting at $0.49/GB"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/evomi.png"></a>
-<a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
 <a href="https://petrosky.io/d4vinci" target="_blank" title="PetroSky delivers cutting-edge VPS hosting."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/petrosky.png"></a>
+<a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
 <a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
+<a href="https://www.nstproxy.com/?type=flow&utm_source=scrapling" target="_blank" title="One Proxy Service, Infinite Solutions at Unbeatable Prices!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/NSTproxy.png"></a>
 
 <!-- /sponsors -->
 
@@ -178,7 +182,7 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 - 🔄 **Smart Element Tracking**: Relocate elements after website changes using intelligent similarity algorithms.
 - 🎯 **Smart Flexible Selection**: CSS selectors, XPath selectors, filter-based search, text search, regex search, and more. 
 - 🔍 **Find Similar Elements**: Automatically locate elements similar to found elements.
-- 🤖 **MCP Server to be used with AI**: Built-in MCP server for AI-assisted Web Scraping and data extraction. The MCP server features custom, powerful capabilities that utilize Scrapling to extract targeted content before passing it to the AI (Claude/Cursor/etc), thereby speeding up operations and reducing costs by minimizing token usage.
+- 🤖 **MCP Server to be used with AI**: Built-in MCP server for AI-assisted Web Scraping and data extraction. The MCP server features custom, powerful capabilities that utilize Scrapling to extract targeted content before passing it to the AI (Claude/Cursor/etc), thereby speeding up operations and reducing costs by minimizing token usage. ([demo video](https://www.youtube.com/watch?v=qyFk3ZNwOxE))
 
 ### High-Performance & battle-tested Architecture
 - 🚀 **Lightning Fast**: Optimized performance outperforming most Python scraping libraries.
@@ -220,7 +224,7 @@ quotes = page.css('.quote .text::text')
 
 # Advanced stealth mode (Keep the browser open until you finish)
 with StealthySession(headless=True, solve_cloudflare=True) as session:
-    page = session.fetch('https://nopecha.com/demo/cloudflare')
+    page = session.fetch('https://nopecha.com/demo/cloudflare', google_search=False)
     data = page.css('#padded_content a')
 
 # Or use one-off request style, it opens the browser for this request, then closes it after finishing
@@ -229,7 +233,7 @@ data = page.css('#padded_content a')
     
 # Full browser automation (Keep the browser open until you finish)
 with DynamicSession(headless=True, disable_resources=False, network_idle=True) as session:
-    page = session.fetch('https://quotes.toscrape.com/')
+    page = session.fetch('https://quotes.toscrape.com/', load_dom=False)
     data = page.xpath('//span[@class="text"]/text()')  # XPath selector if you prefer it
 
 # Or use one-off request style, it opens the browser for this request, then closes it after finishing
@@ -273,7 +277,7 @@ from scrapling.parser import Selector
 
 page = Selector("<html>...</html>")
 ```
-And it works exactly the same!
+And it works precisely the same way!
 
 ### Async Session Management Examples
 ```python
@@ -302,6 +306,8 @@ async with AsyncStealthySession(max_pages=2) as session:
 
 Scrapling v0.3 includes a powerful command-line interface:
 
+[![asciicast](https://asciinema.org/a/736339.svg)](https://asciinema.org/a/736339)
+
 ```bash
 # Launch interactive Web Scraping shell
 scrapling shell
@@ -320,20 +326,20 @@ scrapling extract stealthy-fetch 'https://nopecha.com/demo/cloudflare' captchas.
 
 ## Performance Benchmarks
 
-Scrapling isn't just powerful—it's also blazing fast, and version 0.3 delivers exceptional performance improvements across all operations!
+Scrapling isn't just powerful—it's also blazing fast, and the updates since version 0.3 deliver exceptional performance improvements across all operations!
 
 ### Text Extraction Speed Test (5000 nested elements)
 
 | # |      Library      | Time (ms) | vs Scrapling | 
 |---|:-----------------:|:---------:|:------------:|
-| 1 |     Scrapling     |   1.88    |     1.0x     |
-| 2 |   Parsel/Scrapy   |   1.96    |    1.043x    |
-| 3 |     Raw Lxml      |   2.32    |    1.234x    |
-| 4 |      PyQuery      |   20.2    |     ~11x     |
-| 5 |    Selectolax     |   85.2    |     ~45x     |
-| 6 |  MechanicalSoup   |  1305.84  |    ~695x     |
-| 7 |   BS4 with Lxml   |  1307.92  |    ~696x     |
-| 8 | BS4 with html5lib |  3336.28  |    ~1775x    |
+| 1 |     Scrapling     |   1.92    |     1.0x     |
+| 2 |   Parsel/Scrapy   |   1.99    |    1.036x    |
+| 3 |     Raw Lxml      |   2.33    |    1.214x    |
+| 4 |      PyQuery      |   20.61   |     ~11x     |
+| 5 |    Selectolax     |   80.65   |     ~42x     |
+| 6 |   BS4 with Lxml   |  1283.21  |    ~698x     |
+| 7 |  MechanicalSoup   |  1304.57  |    ~679x     |
+| 8 | BS4 with html5lib |  3331.96  |    ~1735x    |
 
 ### Element Similarity & Text Search Performance
 
@@ -341,8 +347,8 @@ Scrapling's adaptive element finding capabilities significantly outperform alter
 
 |   Library   | Time (ms) | vs Scrapling |
 |-------------|:---------:|:------------:|
-|  Scrapling  |   2.02    |     1.0x     |
-| AutoScraper |   10.26   |    5.08x     |
+|  Scrapling  |   1.87    |     1.0x     |
+| AutoScraper |   10.24   |    5.476x    |
 
 
 > All benchmarks represent averages of 100+ runs. See [benchmarks.py](https://github.com/D4Vinci/Scrapling/blob/main/benchmarks.py) for methodology.
@@ -355,29 +361,33 @@ Scrapling requires Python 3.10 or higher:
 pip install scrapling
 ```
 
-#### Fetchers Setup
-
-If you are going to use any of the fetchers or their classes, then install browser dependencies with
-```bash
-scrapling install
-```
-
-This downloads all browsers with their system dependencies and fingerprint manipulation dependencies.
+Starting with v0.3.2, this installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies.
 
 ### Optional Dependencies
 
-- Install the MCP server feature:
-```bash
-pip install "scrapling[ai]"
-```
-- Install shell features (Web Scraping shell and the `extract` command): 
-```bash
-pip install "scrapling[shell]"
-```
-- Install everything: 
-```bash
-pip install "scrapling[all]"
-```
+1. If you are going to use any of the extra features below, the fetchers, or their classes, then you need to install fetchers' dependencies, and then install their browser dependencies with
+    ```bash
+    pip install "scrapling[fetchers]"
+    
+    scrapling install
+    ```
+
+    This downloads all browsers with their system dependencies and fingerprint manipulation dependencies.
+
+2. Extra features:
+   - Install the MCP server feature:
+       ```bash
+       pip install "scrapling[ai]"
+       ```
+   - Install shell features (Web Scraping shell and the `extract` command): 
+       ```bash
+       pip install "scrapling[shell]"
+       ```
+   - Install everything: 
+       ```bash
+       pip install "scrapling[all]"
+       ```
+   Don't forget that you need to install the browser dependencies with `scrapling install` after any of these extras (if you didn't already)
 
 ## Contributing
 

{scrapling-0.3 → scrapling-0.3.2}/README.md

@@ -68,9 +68,10 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 <!-- sponsors -->
 
 <a href="https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling" target="_blank" title="Evomi is your Swiss Quality Proxy Provider, starting at $0.49/GB"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/evomi.png"></a>
-<a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
 <a href="https://petrosky.io/d4vinci" target="_blank" title="PetroSky delivers cutting-edge VPS hosting."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/petrosky.png"></a>
+<a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
 <a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
+<a href="https://www.nstproxy.com/?type=flow&utm_source=scrapling" target="_blank" title="One Proxy Service, Infinite Solutions at Unbeatable Prices!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/NSTproxy.png"></a>
 
 <!-- /sponsors -->
 
@@ -91,7 +92,7 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 - 🔄 **Smart Element Tracking**: Relocate elements after website changes using intelligent similarity algorithms.
 - 🎯 **Smart Flexible Selection**: CSS selectors, XPath selectors, filter-based search, text search, regex search, and more. 
 - 🔍 **Find Similar Elements**: Automatically locate elements similar to found elements.
-- 🤖 **MCP Server to be used with AI**: Built-in MCP server for AI-assisted Web Scraping and data extraction. The MCP server features custom, powerful capabilities that utilize Scrapling to extract targeted content before passing it to the AI (Claude/Cursor/etc), thereby speeding up operations and reducing costs by minimizing token usage.
+- 🤖 **MCP Server to be used with AI**: Built-in MCP server for AI-assisted Web Scraping and data extraction. The MCP server features custom, powerful capabilities that utilize Scrapling to extract targeted content before passing it to the AI (Claude/Cursor/etc), thereby speeding up operations and reducing costs by minimizing token usage. ([demo video](https://www.youtube.com/watch?v=qyFk3ZNwOxE))
 
 ### High-Performance & battle-tested Architecture
 - 🚀 **Lightning Fast**: Optimized performance outperforming most Python scraping libraries.
@@ -133,7 +134,7 @@ quotes = page.css('.quote .text::text')
 
 # Advanced stealth mode (Keep the browser open until you finish)
 with StealthySession(headless=True, solve_cloudflare=True) as session:
-    page = session.fetch('https://nopecha.com/demo/cloudflare')
+    page = session.fetch('https://nopecha.com/demo/cloudflare', google_search=False)
     data = page.css('#padded_content a')
 
 # Or use one-off request style, it opens the browser for this request, then closes it after finishing
@@ -142,7 +143,7 @@ data = page.css('#padded_content a')
     
 # Full browser automation (Keep the browser open until you finish)
 with DynamicSession(headless=True, disable_resources=False, network_idle=True) as session:
-    page = session.fetch('https://quotes.toscrape.com/')
+    page = session.fetch('https://quotes.toscrape.com/', load_dom=False)
     data = page.xpath('//span[@class="text"]/text()')  # XPath selector if you prefer it
 
 # Or use one-off request style, it opens the browser for this request, then closes it after finishing
@@ -186,7 +187,7 @@ from scrapling.parser import Selector
 
 page = Selector("<html>...</html>")
 ```
-And it works exactly the same!
+And it works precisely the same way!
 
 ### Async Session Management Examples
 ```python
@@ -215,6 +216,8 @@ async with AsyncStealthySession(max_pages=2) as session:
 
 Scrapling v0.3 includes a powerful command-line interface:
 
+[![asciicast](https://asciinema.org/a/736339.svg)](https://asciinema.org/a/736339)
+
 ```bash
 # Launch interactive Web Scraping shell
 scrapling shell
@@ -233,20 +236,20 @@ scrapling extract stealthy-fetch 'https://nopecha.com/demo/cloudflare' captchas.
 
 ## Performance Benchmarks
 
-Scrapling isn't just powerful—it's also blazing fast, and version 0.3 delivers exceptional performance improvements across all operations!
+Scrapling isn't just powerful—it's also blazing fast, and the updates since version 0.3 deliver exceptional performance improvements across all operations!
 
 ### Text Extraction Speed Test (5000 nested elements)
 
 | # |      Library      | Time (ms) | vs Scrapling | 
 |---|:-----------------:|:---------:|:------------:|
-| 1 |     Scrapling     |   1.88    |     1.0x     |
-| 2 |   Parsel/Scrapy   |   1.96    |    1.043x    |
-| 3 |     Raw Lxml      |   2.32    |    1.234x    |
-| 4 |      PyQuery      |   20.2    |     ~11x     |
-| 5 |    Selectolax     |   85.2    |     ~45x     |
-| 6 |  MechanicalSoup   |  1305.84  |    ~695x     |
-| 7 |   BS4 with Lxml   |  1307.92  |    ~696x     |
-| 8 | BS4 with html5lib |  3336.28  |    ~1775x    |
+| 1 |     Scrapling     |   1.92    |     1.0x     |
+| 2 |   Parsel/Scrapy   |   1.99    |    1.036x    |
+| 3 |     Raw Lxml      |   2.33    |    1.214x    |
+| 4 |      PyQuery      |   20.61   |     ~11x     |
+| 5 |    Selectolax     |   80.65   |     ~42x     |
+| 6 |   BS4 with Lxml   |  1283.21  |    ~698x     |
+| 7 |  MechanicalSoup   |  1304.57  |    ~679x     |
+| 8 | BS4 with html5lib |  3331.96  |    ~1735x    |
 
 ### Element Similarity & Text Search Performance
 
@@ -254,8 +257,8 @@ Scrapling's adaptive element finding capabilities significantly outperform alter
 
 |   Library   | Time (ms) | vs Scrapling |
 |-------------|:---------:|:------------:|
-|  Scrapling  |   2.02    |     1.0x     |
-| AutoScraper |   10.26   |    5.08x     |
+|  Scrapling  |   1.87    |     1.0x     |
+| AutoScraper |   10.24   |    5.476x    |
 
 
 > All benchmarks represent averages of 100+ runs. See [benchmarks.py](https://github.com/D4Vinci/Scrapling/blob/main/benchmarks.py) for methodology.
@@ -268,29 +271,33 @@ Scrapling requires Python 3.10 or higher:
 pip install scrapling
 ```
 
-#### Fetchers Setup
-
-If you are going to use any of the fetchers or their classes, then install browser dependencies with
-```bash
-scrapling install
-```
-
-This downloads all browsers with their system dependencies and fingerprint manipulation dependencies.
+Starting with v0.3.2, this installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies.
 
 ### Optional Dependencies
 
-- Install the MCP server feature:
-```bash
-pip install "scrapling[ai]"
-```
-- Install shell features (Web Scraping shell and the `extract` command): 
-```bash
-pip install "scrapling[shell]"
-```
-- Install everything: 
-```bash
-pip install "scrapling[all]"
-```
+1. If you are going to use any of the extra features below, the fetchers, or their classes, then you need to install fetchers' dependencies, and then install their browser dependencies with
+    ```bash
+    pip install "scrapling[fetchers]"
+    
+    scrapling install
+    ```
+
+    This downloads all browsers with their system dependencies and fingerprint manipulation dependencies.
+
+2. Extra features:
+   - Install the MCP server feature:
+       ```bash
+       pip install "scrapling[ai]"
+       ```
+   - Install shell features (Web Scraping shell and the `extract` command): 
+       ```bash
+       pip install "scrapling[shell]"
+       ```
+   - Install everything: 
+       ```bash
+       pip install "scrapling[all]"
+       ```
+   Don't forget that you need to install the browser dependencies with `scrapling install` after any of these extras (if you didn't already)
 
 ## Contributing
 
@@ -319,4 +326,4 @@ This project includes code adapted from:
 - [rebrowser-patches](https://github.com/rebrowser/rebrowser-patches) for stealth improvements
 
 ---
-<div align="center"><small>Designed & crafted with ❤️ by Karim Shoair.</small></div><br>
+<div align="center"><small>Designed & crafted with ❤️ by Karim Shoair.</small></div><br>

{scrapling-0.3 → scrapling-0.3.2}/pyproject.toml

@@ -56,11 +56,15 @@ classifiers = [
     "Typing :: Typed",
 ]
 dependencies = [
-    "lxml>=6.0.0",
+    "lxml>=6.0.1",
     "cssselect>=1.3.0",
-    "click>=8.2.1",
-    "orjson>=3.11.2",
+    "orjson>=3.11.3",
     "tldextract>=5.3.0",
+]
+
+[project.optional-dependencies]
+fetchers = [
+    "click>=8.2.1",
     "curl_cffi>=0.13.0",
     "playwright>=1.52.0",
     "rebrowser-playwright>=1.52.0",
@@ -68,15 +72,15 @@ dependencies = [
     "geoip2>=5.1.0",
     "msgspec>=0.19.0",
 ]
-
-[project.optional-dependencies]
 ai = [
-    "mcp>=1.13.0",
+    "mcp>=1.14.0",
     "markdownify>=1.2.0",
+    "scrapling[fetchers]",
 ]
 shell = [
     "IPython>=8.37",  # The last version that supports Python 3.10
     "markdownify>=1.2.0",
+    "scrapling[fetchers]",
 ]
 all = [
     "scrapling[ai,shell]",

{scrapling-0.3 → scrapling-0.3.2}/scrapling/__init__.py

@@ -1,5 +1,5 @@
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.3"
+__version__ = "0.3.2"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 

{scrapling-0.3 → scrapling-0.3.2}/scrapling/cli.py

@@ -2,14 +2,18 @@ from pathlib import Path
 from subprocess import check_output
 from sys import executable as python_executable
 
-from scrapling.core.utils import log
-from scrapling.engines.toolbelt import Response
+from scrapling.engines.toolbelt.custom import Response
+from scrapling.core.utils import log, _CookieParser, _ParseHeaders
 from scrapling.core._types import List, Optional, Dict, Tuple, Any, Callable
-from scrapling.fetchers import Fetcher, DynamicFetcher, StealthyFetcher
-from scrapling.core.shell import Convertor, _CookieParser, _ParseHeaders
 
 from orjson import loads as json_loads, JSONDecodeError
-from click import command, option, Choice, group, argument
+
+try:
+    from click import command, option, Choice, group, argument
+except (ImportError, ModuleNotFoundError) as e:
+    raise ModuleNotFoundError(
+        "You need to install scrapling with any of the extras to enable Shell commands. See: https://scrapling.readthedocs.io/en/latest/#installation"
+    ) from e
 
 __OUTPUT_FILE_HELP__ = "The output file path can be an HTML file, a Markdown file of the HTML content, or the text content itself. Use file extensions (`.html`/`.md`/`.txt`) respectively."
 __PACKAGE_DIR__ = Path(__file__).parent
@@ -40,6 +44,8 @@ def __Request_and_Save(
     **kwargs,
 ) -> None:
     """Make a request using the specified fetcher function and save the result"""
+    from scrapling.core.shell import Convertor
+
     # Handle relative paths - convert to an absolute path based on the current working directory
     output_path = Path(output_file)
     if not output_path.is_absolute():
@@ -72,14 +78,10 @@ def __ParseExtractArguments(
     return parsed_headers, parsed_cookies, parsed_params, parsed_json
 
 
-def __BuildRequest(
-    headers: List[str], cookies: str, params: str, json: Optional[str] = None, **kwargs
-) -> Dict:
+def __BuildRequest(headers: List[str], cookies: str, params: str, json: Optional[str] = None, **kwargs) -> Dict:
     """Build a request object using the specified arguments"""
     # Parse parameters
-    parsed_headers, parsed_cookies, parsed_params, parsed_json = (
-        __ParseExtractArguments(headers, cookies, params, json)
-    )
+    parsed_headers, parsed_cookies, parsed_params, parsed_json = __ParseExtractArguments(headers, cookies, params, json)
     # Build request arguments
     request_kwargs = {
         "headers": parsed_headers if parsed_headers else None,
@@ -106,10 +108,7 @@ def __BuildRequest(
     help="Force Scrapling to reinstall all Fetchers dependencies",
 )
 def install(force):  # pragma: no cover
-    if (
-        force
-        or not __PACKAGE_DIR__.joinpath(".scrapling_dependencies_installed").exists()
-    ):
+    if force or not __PACKAGE_DIR__.joinpath(".scrapling_dependencies_installed").exists():
         __Execute(
             [python_executable, "-m", "playwright", "install", "chromium"],
             "Playwright browsers",
@@ -158,9 +157,7 @@ def mcp():
     "level",
     is_flag=False,
     default="debug",
-    type=Choice(
-        ["debug", "info", "warning", "error", "critical", "fatal"], case_sensitive=False
-    ),
+    type=Choice(["debug", "info", "warning", "error", "critical", "fatal"], case_sensitive=False),
     help="Log level (default: DEBUG)",
 )
 def shell(code, level):
@@ -178,9 +175,7 @@ def extract():
     pass
 
 
-@extract.command(
-    help=f"Perform a GET request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Perform a GET request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option(
@@ -190,9 +185,7 @@ def extract():
     help='HTTP headers in format "Key: Value" (can be used multiple times)',
 )
 @option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
-@option(
-    "--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)"
-)
+@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
 @option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
 @option(
     "--css-selector",
@@ -264,12 +257,12 @@ def get(
         impersonate=impersonate,
         proxy=proxy,
     )
+    from scrapling.fetchers import Fetcher
+
     __Request_and_Save(Fetcher.get, url, output_file, css_selector, **kwargs)
 
 
-@extract.command(
-    help=f"Perform a POST request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Perform a POST request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option(
@@ -285,9 +278,7 @@ def get(
     help='HTTP headers in format "Key: Value" (can be used multiple times)',
 )
 @option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
-@option(
-    "--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)"
-)
+@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
 @option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
 @option(
     "--css-selector",
@@ -364,12 +355,12 @@ def post(
         proxy=proxy,
         data=data,
     )
+    from scrapling.fetchers import Fetcher
+
     __Request_and_Save(Fetcher.post, url, output_file, css_selector, **kwargs)
 
 
-@extract.command(
-    help=f"Perform a PUT request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Perform a PUT request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option("--data", "-d", help="Form data to include in the request body")
@@ -381,9 +372,7 @@ def post(
     help='HTTP headers in format "Key: Value" (can be used multiple times)',
 )
 @option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
-@option(
-    "--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)"
-)
+@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
 @option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
 @option(
     "--css-selector",
@@ -460,12 +449,12 @@ def put(
         proxy=proxy,
         data=data,
     )
+    from scrapling.fetchers import Fetcher
+
     __Request_and_Save(Fetcher.put, url, output_file, css_selector, **kwargs)
 
 
-@extract.command(
-    help=f"Perform a DELETE request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Perform a DELETE request and save the content to a file.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option(
@@ -475,9 +464,7 @@ def put(
     help='HTTP headers in format "Key: Value" (can be used multiple times)',
 )
 @option("--cookies", help='Cookies string in format "name1=value1; name2=value2"')
-@option(
-    "--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)"
-)
+@option("--timeout", type=int, default=30, help="Request timeout in seconds (default: 30)")
 @option("--proxy", help='Proxy URL in format "http://username:password@host:port"')
 @option(
     "--css-selector",
@@ -549,12 +536,12 @@ def delete(
         impersonate=impersonate,
         proxy=proxy,
     )
+    from scrapling.fetchers import Fetcher
+
     __Request_and_Save(Fetcher.delete, url, output_file, css_selector, **kwargs)
 
 
-@extract.command(
-    help=f"Use DynamicFetcher to fetch content with browser automation.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Use DynamicFetcher to fetch content with browser automation.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option(
@@ -591,9 +578,7 @@ def delete(
 )
 @option("--wait-selector", help="CSS selector to wait for before proceeding")
 @option("--locale", default="en-US", help="Browser locale (default: en-US)")
-@option(
-    "--stealth/--no-stealth", default=False, help="Enable stealth mode (default: False)"
-)
+@option("--stealth/--no-stealth", default=False, help="Enable stealth mode (default: False)")
 @option(
     "--hide-canvas/--show-canvas",
     default=False,
@@ -672,12 +657,12 @@ def fetch(
     if parsed_headers:
         kwargs["extra_headers"] = parsed_headers
 
+    from scrapling.fetchers import DynamicFetcher
+
     __Request_and_Save(DynamicFetcher.fetch, url, output_file, css_selector, **kwargs)
 
 
-@extract.command(
-    help=f"Use StealthyFetcher to fetch content with advanced stealth features.\n\n{__OUTPUT_FILE_HELP__}"
-)
+@extract.command(help=f"Use StealthyFetcher to fetch content with advanced stealth features.\n\n{__OUTPUT_FILE_HELP__}")
 @argument("url", required=True)
 @argument("output_file", required=True)
 @option(
@@ -821,6 +806,8 @@ def stealthy_fetch(
     if parsed_headers:
         kwargs["extra_headers"] = parsed_headers
 
+    from scrapling.fetchers import StealthyFetcher
+
     __Request_and_Save(StealthyFetcher.fetch, url, output_file, css_selector, **kwargs)
 
 

{scrapling-0.3 → scrapling-0.3.2}/scrapling/core/_html_utils.py

@@ -269,17 +269,13 @@ name2codepoint = {
 }
 
 
-def to_unicode(
-    text: StrOrBytes, encoding: Optional[str] = None, errors: str = "strict"
-) -> str:
+def to_unicode(text: StrOrBytes, encoding: Optional[str] = None, errors: str = "strict") -> str:
     """Return the Unicode representation of a bytes object `text`. If `text`
     is already a Unicode object, return it as-is."""
     if isinstance(text, str):
         return text
     if not isinstance(text, (bytes, str)):
-        raise TypeError(
-            f"to_unicode must receive bytes or str, got {type(text).__name__}"
-        )
+        raise TypeError(f"to_unicode must receive bytes or str, got {type(text).__name__}")
     if encoding is None:
         encoding = "utf-8"
     return text.decode(encoding, errors)
@@ -328,9 +324,7 @@ def _replace_entities(
             entity_name = groups["named"]
             if entity_name.lower() in keep:
                 return m.group(0)
-            number = name2codepoint.get(entity_name) or name2codepoint.get(
-                entity_name.lower()
-            )
+            number = name2codepoint.get(entity_name) or name2codepoint.get(entity_name.lower())
         if number is not None:
             # Browsers typically
             # interpret numeric character references in the 80-9F range as representing the characters mapped