scrapling 0.2.97__py3-none-any.whl → 0.2.99__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,290 @@
1
+ Metadata-Version: 2.4
2
+ Name: scrapling
3
+ Version: 0.2.99
4
+ Summary: Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy again! In an internet filled with complications,
5
+ Home-page: https://github.com/D4Vinci/Scrapling
6
+ Author: Karim Shoair
7
+ Author-email: karim.shoair@pm.me
8
+ License: BSD
9
+ Project-URL: Documentation, https://scrapling.readthedocs.io/en/latest/
10
+ Project-URL: Source, https://github.com/D4Vinci/Scrapling
11
+ Project-URL: Tracker, https://github.com/D4Vinci/Scrapling/issues
12
+ Classifier: Operating System :: OS Independent
13
+ Classifier: Development Status :: 4 - Beta
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: License :: OSI Approved :: BSD License
16
+ Classifier: Natural Language :: English
17
+ Classifier: Topic :: Internet :: WWW/HTTP
18
+ Classifier: Topic :: Text Processing :: Markup
19
+ Classifier: Topic :: Internet :: WWW/HTTP :: Browsers
20
+ Classifier: Topic :: Text Processing :: Markup :: HTML
21
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
22
+ Classifier: Programming Language :: Python :: 3
23
+ Classifier: Programming Language :: Python :: 3 :: Only
24
+ Classifier: Programming Language :: Python :: 3.9
25
+ Classifier: Programming Language :: Python :: 3.10
26
+ Classifier: Programming Language :: Python :: 3.11
27
+ Classifier: Programming Language :: Python :: 3.12
28
+ Classifier: Programming Language :: Python :: 3.13
29
+ Classifier: Programming Language :: Python :: Implementation :: CPython
30
+ Classifier: Typing :: Typed
31
+ Requires-Python: >=3.9
32
+ Description-Content-Type: text/markdown
33
+ License-File: LICENSE
34
+ Requires-Dist: lxml>=5.0
35
+ Requires-Dist: cssselect>=1.2
36
+ Requires-Dist: click
37
+ Requires-Dist: w3lib
38
+ Requires-Dist: orjson>=3
39
+ Requires-Dist: tldextract
40
+ Requires-Dist: httpx[brotli,socks,zstd]
41
+ Requires-Dist: playwright>=1.49.1
42
+ Requires-Dist: rebrowser-playwright>=1.49.1
43
+ Requires-Dist: camoufox[geoip]>=0.4.11
44
+ Dynamic: author
45
+ Dynamic: author-email
46
+ Dynamic: classifier
47
+ Dynamic: description
48
+ Dynamic: description-content-type
49
+ Dynamic: home-page
50
+ Dynamic: license
51
+ Dynamic: license-file
52
+ Dynamic: project-url
53
+ Dynamic: requires-dist
54
+ Dynamic: requires-python
55
+ Dynamic: summary
56
+
57
+ # 🕷️ Scrapling: Undetectable, Lightning-Fast, and Easy Web Scraping with Python
58
+ <p align="center">
59
+ <a href="https://github.com/D4Vinci/Scrapling/actions/workflows/tests.yml" alt="Tests">
60
+ <img alt="Tests" src="https://github.com/D4Vinci/Scrapling/actions/workflows/tests.yml/badge.svg"></a>
61
+ <a href="https://badge.fury.io/py/Scrapling" alt="PyPI version">
62
+ <img alt="PyPI version" src="https://badge.fury.io/py/Scrapling.svg"></a>
63
+ <a href="https://pepy.tech/project/scrapling" alt="PyPI Downloads">
64
+ <img alt="PyPI Downloads" src="https://static.pepy.tech/badge/scrapling"></a>
65
+ <br/>
66
+ <a href="https://pypi.org/project/scrapling/" alt="Supported Python versions">
67
+ <img alt="Supported Python versions" src="https://img.shields.io/pypi/pyversions/scrapling.svg"></a>
68
+ </p>
69
+ <p align="center">
70
+ <a href="https://scrapling.readthedocs.io/en/latest/#installation">
71
+ Installation
72
+ </a>
73
+ ·
74
+ <a href="https://scrapling.readthedocs.io/en/latest/overview/">
75
+ Overview
76
+ </a>
77
+ ·
78
+ <a href="https://scrapling.readthedocs.io/en/latest/parsing/selection/">
79
+ Selection methods
80
+ </a>
81
+ ·
82
+ <a href="https://scrapling.readthedocs.io/en/latest/fetching/choosing/">
83
+ Choosing a fetcher
84
+ </a>
85
+ ·
86
+ <a href="https://scrapling.readthedocs.io/en/latest/tutorials/migrating_from_beautifulsoup/">
87
+ Migrating from Beautifulsoup
88
+ </a>
89
+ </p>
90
+
91
+ Dealing with failing web scrapers due to anti-bot protections or website changes? Meet Scrapling.
92
+
93
+ Scrapling is a high-performance, intelligent web scraping library for Python that automatically adapts to website changes while significantly outperforming popular alternatives. For both beginners and experts, Scrapling provides powerful features while maintaining simplicity.
94
+
95
+ ```python
96
+ >> from scrapling.fetchers import Fetcher, AsyncFetcher, StealthyFetcher, PlayWrightFetcher
97
+ >> StealthyFetcher.auto_match = True
98
+ # Fetch websites' source under the radar!
99
+ >> page = StealthyFetcher.fetch('https://example.com', headless=True, network_idle=True)
100
+ >> print(page.status)
101
+ 200
102
+ >> products = page.css('.product', auto_save=True) # Scrape data that survives website design changes!
103
+ >> # Later, if the website structure changes, pass `auto_match=True`
104
+ >> products = page.css('.product', auto_match=True) # and Scrapling still finds them!
105
+ ```
106
+
107
+ # Sponsors
108
+
109
+ [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!
110
+
111
+ Deep SerpApi is a dedicated search engine designed for large language models (LLMs) and AI agents. It aims to provide real-time, accurate, and unbiased information to help AI applications retrieve and process data efficiently.
112
+ - covering 20+ Google SERP scenarios and mainstream search engines.
113
+ - support real-time data updates to ensure real-time and accurate information.
114
+ - It can integrate information from all available online channels and search engines.
115
+ - 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.
116
+ - **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.
117
+ - 🚀 **Scraping API**: Effortless and highly customizable data extraction with a single API call, providing structured data from any website.
118
+ - ⚡ **Scraping Browser**: AI-powered and LLM-driven, it simulates human-like behavior with genuine fingerprints and headless browser support, ensuring seamless, block-free scraping.
119
+ - 🌐 **Proxies**: Use high-quality, rotating proxies to scrape top platforms like Amazon, Shopee, and more, with global coverage in 195+ countries.
120
+
121
+
122
+ [![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)
123
+ ---
124
+
125
+ [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**
126
+
127
+ - 👩‍💻 **$0.49 per GB Residential Proxies**: Our price is unbeatable
128
+ - 👩‍💻 **24/7 Expert Support**: We will join your Slack Channel
129
+ - 🌍 **Global Presence**: Available in 150+ Countries
130
+ - ⚡ **Low Latency**
131
+ - 🔒 **Swiss Quality and Privacy**
132
+ - 🎁 **Free Trial**
133
+ - 🛡️ **99.9% Uptime**
134
+ - 🤝 **Special IP Pool selection**: Optimize for fast, quality or quantity of ips
135
+ - 🔧 **Easy Integration**: Compatible with most software and programming languages
136
+
137
+ [![Evomi Banner](https://my.evomi.com/images/brand/cta.png)](https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling)
138
+ ---
139
+
140
+ ## Key Features
141
+
142
+ ### Fetch websites as you prefer with async support
143
+ - **HTTP Requests**: Fast and stealthy HTTP requests with the `Fetcher` class.
144
+ - **Dynamic Loading & Automation**: Fetch dynamic websites with the `PlayWrightFetcher` class through your real browser, Scrapling's stealth mode, Playwright's Chrome browser, or [NSTbrowser](https://app.nstbrowser.io/r/1vO5e5)'s browserless!
145
+ - **Anti-bot Protections Bypass**: Easily bypass protections with the `StealthyFetcher` and `PlayWrightFetcher` classes.
146
+
147
+ ### Adaptive Scraping
148
+ - 🔄 **Smart Element Tracking**: Relocate elements after website changes using an intelligent similarity system and integrated storage.
149
+ - 🎯 **Flexible Selection**: CSS selectors, XPath selectors, filters-based search, text search, regex search, and more.
150
+ - 🔍 **Find Similar Elements**: Automatically locate elements similar to the element you found!
151
+ - 🧠 **Smart Content Scraping**: Extract data from multiple websites using Scrapling's powerful features without specific selectors.
152
+
153
+ ### High Performance
154
+ - 🚀 **Lightning Fast**: Built from the ground up with performance in mind, outperforming most popular Python scraping libraries.
155
+ - 🔋 **Memory Efficient**: Optimized data structures for minimal memory footprint.
156
+ - ⚡ **Fast JSON serialization**: 10x faster than standard library.
157
+
158
+ ### Developer Friendly
159
+ - 🛠️ **Powerful Navigation API**: Easy DOM traversal in all directions.
160
+ - 🧬 **Rich Text Processing**: All strings have built-in regex, cleaning methods, and more. All elements' attributes are optimized dictionaries with added methods that consume less memory than standard dictionaries.
161
+ - 📝 **Auto Selectors Generation**: Generate robust short and full CSS/XPath selectors for any element.
162
+ - 🔌 **Familiar API**: Similar to Scrapy/BeautifulSoup and the same pseudo-elements used in Scrapy.
163
+ - 📘 **Type hints**: Complete type/doc-strings coverage for future-proofing and best autocompletion support.
164
+
165
+ ## Getting Started
166
+
167
+ ```python
168
+ from scrapling.fetchers import Fetcher
169
+
170
+ # Do HTTP GET request to a web page and create an Adaptor instance
171
+ page = Fetcher.get('https://quotes.toscrape.com/', stealthy_headers=True)
172
+ # Get all text content from all HTML tags in the page except the `script` and `style` tags
173
+ page.get_all_text(ignore_tags=('script', 'style'))
174
+
175
+ # Get all quotes elements; any of these methods will return a list of strings directly (TextHandlers)
176
+ quotes = page.css('.quote .text::text') # CSS selector
177
+ quotes = page.xpath('//span[@class="text"]/text()') # XPath
178
+ quotes = page.css('.quote').css('.text::text') # Chained selectors
179
+ quotes = [element.text for element in page.css('.quote .text')] # Slower than bulk query above
180
+
181
+ # Get the first quote element
182
+ quote = page.css_first('.quote') # same as page.css('.quote').first or page.css('.quote')[0]
183
+
184
+ # Tired of selectors? Use find_all/find
185
+ # Get all 'div' HTML tags that one of its 'class' values is 'quote'
186
+ quotes = page.find_all('div', {'class': 'quote'})
187
+ # Same as
188
+ quotes = page.find_all('div', class_='quote')
189
+ quotes = page.find_all(['div'], class_='quote')
190
+ quotes = page.find_all(class_='quote') # and so on...
191
+
192
+ # Working with elements
193
+ quote.html_content # Get the Inner HTML of this element
194
+ quote.prettify() # Prettified version of Inner HTML above
195
+ quote.attrib # Get that element's attributes
196
+ quote.path # DOM path to element (List of all ancestors from <html> tag till the element itself)
197
+ ```
198
+ To keep it simple, all methods can be chained on top of each other!
199
+
200
+ > [!NOTE]
201
+ > Check out the full documentation from [here](https://scrapling.readthedocs.io/en/latest/)
202
+
203
+ ## Parsing Performance
204
+
205
+ Scrapling isn't just powerful - it's also blazing fast. Scrapling implements many best practices, design patterns, and numerous optimizations to save fractions of seconds. All of that while focusing exclusively on parsing HTML documents.
206
+ Here are benchmarks comparing Scrapling to popular Python libraries in two tests.
207
+
208
+ ### Text Extraction Speed Test (5000 nested elements).
209
+
210
+ This test consists of extracting the text content of 5000 nested div elements.
211
+
212
+
213
+ | # | Library | Time (ms) | vs Scrapling |
214
+ |---|:-----------------:|:---------:|:------------:|
215
+ | 1 | Scrapling | 5.44 | 1.0x |
216
+ | 2 | Parsel/Scrapy | 5.53 | 1.017x |
217
+ | 3 | Raw Lxml | 6.76 | 1.243x |
218
+ | 4 | PyQuery | 21.96 | 4.037x |
219
+ | 5 | Selectolax | 67.12 | 12.338x |
220
+ | 6 | BS4 with Lxml | 1307.03 | 240.263x |
221
+ | 7 | MechanicalSoup | 1322.64 | 243.132x |
222
+ | 8 | BS4 with html5lib | 3373.75 | 620.175x |
223
+
224
+ As you see, Scrapling is on par with Scrapy and slightly faster than Lxml, which both libraries are built on top of. These are the closest results to Scrapling. PyQuery is also built on top of Lxml, but Scrapling is four times faster.
225
+
226
+ ### Extraction By Text Speed Test
227
+
228
+ Scrapling can find elements based on its text content and find elements similar to these elements. The only known library with these two features, too, is AutoScraper.
229
+
230
+ So, we compared this to see how fast Scrapling can be in these two tasks compared to AutoScraper.
231
+
232
+ Here are the results:
233
+
234
+ | Library | Time (ms) | vs Scrapling |
235
+ |-------------|:---------:|:------------:|
236
+ | Scrapling | 2.51 | 1.0x |
237
+ | AutoScraper | 11.41 | 4.546x |
238
+
239
+ Scrapling can find elements with more methods and returns the entire element's `Adaptor` object, not only text like AutoScraper. So, to make this test fair, both libraries will extract an element with text, find similar elements, and then extract the text content for all of them.
240
+
241
+ As you see, Scrapling is still 4.5 times faster at the same task.
242
+
243
+ If we made Scrapling extract the elements only without stopping to extract each element's text, we would get speed twice as fast as this, but as I said, to make it fair comparison a bit :smile:
244
+
245
+ > All benchmarks' results are an average of 100 runs. See our [benchmarks.py](https://github.com/D4Vinci/Scrapling/blob/main/benchmarks.py) for methodology and to run your comparisons.
246
+
247
+ ## Installation
248
+ Scrapling is a breeze to get started with. Starting from version 0.2.9, we require at least Python 3.9 to work.
249
+ ```bash
250
+ pip3 install scrapling
251
+ ```
252
+ Then run this command to install browsers' dependencies needed to use Fetcher classes
253
+ ```bash
254
+ scrapling install
255
+ ```
256
+ If you have any installation issues, please open an issue.
257
+
258
+
259
+ ## More Sponsors!
260
+ <a href="https://serpapi.com/?utm_source=scrapling"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png" height="500" alt="SerpApi Banner" ></a>
261
+
262
+
263
+ ## Contributing
264
+ Everybody is invited and welcome to contribute to Scrapling. There is a lot to do!
265
+
266
+ Please read the [contributing file](https://github.com/D4Vinci/Scrapling/blob/main/CONTRIBUTING.md) before doing anything.
267
+
268
+ ## Disclaimer for Scrapling Project
269
+ > [!CAUTION]
270
+ > This library is provided for educational and research purposes only. By using this library, you agree to comply with local and international data scraping and privacy laws. The authors and contributors are not responsible for any misuse of this software. This library should not be used to violate the rights of others, for unethical purposes, or to use data in an unauthorized or illegal manner. Do not use it on any website unless you have permission from the website owner or within their allowed rules, such as the `robots.txt` file.
271
+
272
+ ## License
273
+ This work is licensed under BSD-3
274
+
275
+ ## Acknowledgments
276
+ This project includes code adapted from:
277
+ - Parsel (BSD License) - Used for [translator](https://github.com/D4Vinci/Scrapling/blob/main/scrapling/translator.py) submodule
278
+
279
+ ## Thanks and References
280
+ - [Daijro](https://github.com/daijro)'s brilliant work on both [BrowserForge](https://github.com/daijro/browserforge) and [Camoufox](https://github.com/daijro/camoufox)
281
+ - [Vinyzu](https://github.com/Vinyzu)'s work on Playwright's mock on [Botright](https://github.com/Vinyzu/Botright)
282
+ - [brotector](https://github.com/kaliiiiiiiiii/brotector)
283
+ - [fakebrowser](https://github.com/kkoooqq/fakebrowser)
284
+ - [rebrowser-patches](https://github.com/rebrowser/rebrowser-patches)
285
+
286
+ ## Known Issues
287
+ - In the auto-matching save process, the unique properties of the first element from the selection results are the only ones that get saved. If the selector you are using selects different elements on the page in different locations, auto-matching will return the first element to you only when you relocate it later. This doesn't include combined CSS selectors (Using commas to combine more than one selector, for example), as these selectors get separated, and each selector gets executed alone.
288
+
289
+ ---
290
+ <div align="center"><small>Designed & crafted with ❤️ by Karim Shoair.</small></div><br>
@@ -1,25 +1,25 @@
1
- scrapling/__init__.py,sha256=5yeUml2K0xHe2NAALM2x2hGSl_ORcEttIZL17b1cWtg,500
1
+ scrapling/__init__.py,sha256=hNIkfkiY42w_VSw9-Flicz83FYGGdXvY3uWMtcoyJV8,1510
2
2
  scrapling/cli.py,sha256=7yTsMhVAqqS8Z27T5dFKrR9_X8vuFjBlwYgAF22W7T8,1292
3
- scrapling/defaults.py,sha256=sdXeZjXEX7PmCtaa0weK0nRrAUzqZukNNqipZ_sltYE,469
4
- scrapling/fetchers.py,sha256=xwVCjAg0VCXwhB2igSLQvb0D0bOPGfg5WNtxgE7m-W0,34987
5
- scrapling/parser.py,sha256=U6qFV23qeeX1pYl6mw0TZEL4FlaQw6puaoDTldUpi-M,54328
3
+ scrapling/defaults.py,sha256=07g4E7-A8QPkpDuEW4EP0tI4m_KBQQWIoi7dbRxZyXI,1413
4
+ scrapling/fetchers.py,sha256=fsHq27mAa8hFMl263igdUpT7pphUhYFnxLf025bE6DQ,41718
5
+ scrapling/parser.py,sha256=4BWeHYszXZAN9_t-5G5zE7ZaUSwj0vP8e_tsTfe4hn0,53957
6
6
  scrapling/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
7
7
  scrapling/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
8
8
  scrapling/core/_types.py,sha256=dKVi_dUxdxNtTr7sj7ySkHXDfrsmjFTfpCQeO5tGuBY,670
9
9
  scrapling/core/custom_types.py,sha256=EWGx5t5scHEB1SMsitzc8duskq-5f-Qaj40IWkNTRzM,12947
10
10
  scrapling/core/mixins.py,sha256=sozbpaGL1_O_x3U-ABM5aYWpnxpCLfdbcA9SG3P7weY,3532
11
- scrapling/core/storage_adaptors.py,sha256=EkSE8LlOS9SggFblBNzgyEp0fLxl8dqYU3-MAuXUitY,6216
12
- scrapling/core/translator.py,sha256=ojDmNi5pFZE6Ke-AiSsTilXiPRdR8yhX3o-uVGMkap8,5236
13
- scrapling/core/utils.py,sha256=0e3jD029CXj3gfA_MIKcBC0Mai9fXW2scIuoKtHy1e8,3704
11
+ scrapling/core/storage_adaptors.py,sha256=gZbUpHtLOL7o_oZbES_o40r39zShxTeTM8YK6dXA5Zo,6214
12
+ scrapling/core/translator.py,sha256=3a2VX9KR-q-GzwT1OgGDv1UlzIkvBggkQXUdiMyL-4c,5277
13
+ scrapling/core/utils.py,sha256=KX88B3tV1-SgCAr69TUN3LfmsTDcLnEhYJiPuWd31yA,3704
14
14
  scrapling/engines/__init__.py,sha256=zA7tzqcDXP0hllwmjVewNHWipIA4JSU9mRG4J-cud0c,267
15
- scrapling/engines/camo.py,sha256=oYKA0l3EpOcQW2APRj5FEmslqtp9A8i_ZljqlKvIDeI,16129
15
+ scrapling/engines/camo.py,sha256=4q8f1uHTlyNVWhOF-a7xUJFzquCJ7bd0K4huhhoa5pY,18398
16
16
  scrapling/engines/constants.py,sha256=Gb_nXFoBB4ujJkd05SKkenMe1UDiRYQA3dkmA3DunLg,3723
17
- scrapling/engines/pw.py,sha256=_fy8mhkVrOnb_Qho8zKCjFyd1Y_kr2mkdo0PHrBks4M,21371
18
- scrapling/engines/static.py,sha256=okrEIFfYaxqVuIXPanxQDxQpN8i88AgWODo7Dnex2EI,9306
17
+ scrapling/engines/pw.py,sha256=1_Njrv3hOtXfx5dQya2ivaGuX7d4rIwfBtYvQcxgsv4,23339
18
+ scrapling/engines/static.py,sha256=EjdaR0beqWfEKKavT7vlBnozoayQaVpqeVtaOuzd384,9306
19
19
  scrapling/engines/toolbelt/__init__.py,sha256=VQDdYm1zY9Apno6d8UrULk29vUjllZrQqD8mXL1E2Fc,402
20
- scrapling/engines/toolbelt/custom.py,sha256=dwpuEHNOd9uJbMf7sx8sXsYZhozSXStrwqfpooce1Wk,12811
21
- scrapling/engines/toolbelt/fingerprints.py,sha256=spJMij0qBGvbSlVjv9xJWCF8KFDf6xnNz5fWtXWhrzY,2927
22
- scrapling/engines/toolbelt/navigation.py,sha256=KyFQ4vHS4jR7z378VRGtUeXQHWr5NMy5nNp2-c_Evk8,4566
20
+ scrapling/engines/toolbelt/custom.py,sha256=m5RUTmqaJ7lF2LhVAOzJGIRNEYtxdSx0JgCfHpy0X1A,13428
21
+ scrapling/engines/toolbelt/fingerprints.py,sha256=Zzoqq3p6X_8D7eTxACz3z96cBZWWK61iKOGo2sZUtlg,2924
22
+ scrapling/engines/toolbelt/navigation.py,sha256=fMjDgicqy2MoZZll2h5EvrrxkL6yNrC09v8isTpwAt0,4565
23
23
  scrapling/engines/toolbelt/bypasses/navigator_plugins.js,sha256=tbnnk3nCXB6QEQnOhDlu3n-s7lnUTAkrUsjP6FDQIQg,2104
24
24
  scrapling/engines/toolbelt/bypasses/notification_permission.js,sha256=poPM3o5WYgEX-EdiUfDCllpWfc3Umvw4jr2u6O6elus,237
25
25
  scrapling/engines/toolbelt/bypasses/pdf_viewer.js,sha256=mKjjSuP1-BOGC_2WhRYHJo_LP7lTBi2KXmP_zsHO_tI,173
@@ -27,23 +27,23 @@ scrapling/engines/toolbelt/bypasses/playwright_fingerprint.js,sha256=3RP1AE_XZRv
27
27
  scrapling/engines/toolbelt/bypasses/screen_props.js,sha256=fZEuHMQ1-fYuxxUMoQXUvVWYUkPUbblkfMfpiLvBY7w,599
28
28
  scrapling/engines/toolbelt/bypasses/webdriver_fully.js,sha256=hdJw4clRAJQqIdq5gIFC_eC-x7C1i2ab01KV5ylmOBs,728
29
29
  scrapling/engines/toolbelt/bypasses/window_chrome.js,sha256=D7hqzNGGDorh8JVlvm2YIv7Bk2CoVkG55MDIdyqhT1w,6808
30
+ scrapling-0.2.99.dist-info/licenses/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
30
31
  tests/__init__.py,sha256=YHFB5ftzgLQVh6gbPfbYcY4yOS9DOBp5dBa6I-qtm8U,32
31
32
  tests/fetchers/__init__.py,sha256=6H4NgARhyTcGGd3dNCKQJ8kUFdrAEMSScQL7Ga_vU3c,43
32
33
  tests/fetchers/test_utils.py,sha256=ANFu-4FFhtyGFGIwJksUO2M2tTTcKU2M_t6F2aav8lM,4967
33
34
  tests/fetchers/async/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
34
- tests/fetchers/async/test_camoufox.py,sha256=BANJ0TVqEdsjkYlsyU-q_spfaMsqTLOBQU8LUDurL9I,3685
35
- tests/fetchers/async/test_httpx.py,sha256=6WgsvqV1-rYTjZ9na5x-wt49C3Ur9D99HXBFbewO0gc,3888
36
- tests/fetchers/async/test_playwright.py,sha256=rr_3vB9LWclbl7PBNMH2MNU6CsirvJAIx_LsI9mLil0,4106
35
+ tests/fetchers/async/test_camoufox.py,sha256=-Ar5b5d14S3k-S0j2p6yM-8sibaqMBaB9TK_iU8aCIA,3702
36
+ tests/fetchers/async/test_httpx.py,sha256=yABAGK1ZEvceZAV5O4WB25x0j8amb2lwaHqbEizPSzM,3903
37
+ tests/fetchers/async/test_playwright.py,sha256=ubKX8BKZ8VImI6an-cIIcs5RCrrtZiTA_CAkipnO-UY,4125
37
38
  tests/fetchers/sync/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
38
- tests/fetchers/sync/test_camoufox.py,sha256=IcDXPAWSSJnYT6psDFKSbCeym5n7hCrMPYQEghaOX3A,3165
39
- tests/fetchers/sync/test_httpx.py,sha256=xItYWjnDOIswKJzua2tDq8Oy43nTeFl0O1bci7lzGmg,3615
40
- tests/fetchers/sync/test_playwright.py,sha256=MEyDRaMyxDIWupG7f_xz0f0jd9Cpbd5rXCPz6qUy8cs,3818
39
+ tests/fetchers/sync/test_camoufox.py,sha256=-N4GrvOd37vDECUzZko9IJUBs3xrDyGw1nSUDwiJnnI,3182
40
+ tests/fetchers/sync/test_httpx.py,sha256=oJeDGqCAzVcHawAZ2_-guUiEKMgvgQOuLkA24RVpP5E,3624
41
+ tests/fetchers/sync/test_playwright.py,sha256=OIcI3I4Tp8zvoJEgHvlP_nHyf5Kf1cMeKcxT6oFmGB4,3837
41
42
  tests/parser/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
42
43
  tests/parser/test_automatch.py,sha256=SxsNdExE8zz8AcPRQFBUjZ3Q_1-tPOd9dzVvMSZpOYQ,4908
43
44
  tests/parser/test_general.py,sha256=dyfOsc8lleoY4AxcfDUBUaD1i95xecfYuTUhKBsYjwo,12100
44
- scrapling-0.2.97.dist-info/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
45
- scrapling-0.2.97.dist-info/METADATA,sha256=VnP3UEy6RcQytld-8ZYSF0Cpdd4fb-tKoX01jajFneo,69666
46
- scrapling-0.2.97.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
47
- scrapling-0.2.97.dist-info/entry_points.txt,sha256=DHyt2Blxy0P5OE2HRcP95Wz9_xo2ERCDcNqrJjYS3o8,49
48
- scrapling-0.2.97.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
49
- scrapling-0.2.97.dist-info/RECORD,,
45
+ scrapling-0.2.99.dist-info/METADATA,sha256=93jrvv1iAQ7kWOVDrn9wEvgSOS8WmE3cMpjzpHscD1s,16054
46
+ scrapling-0.2.99.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
47
+ scrapling-0.2.99.dist-info/entry_points.txt,sha256=DHyt2Blxy0P5OE2HRcP95Wz9_xo2ERCDcNqrJjYS3o8,49
48
+ scrapling-0.2.99.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
49
+ scrapling-0.2.99.dist-info/RECORD,,
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: setuptools (76.0.0)
2
+ Generator: setuptools (78.1.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5
 
@@ -3,13 +3,15 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling import StealthyFetcher
5
5
 
6
+ StealthyFetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  @pytest.mark.asyncio
9
11
  class TestStealthyFetcher:
10
12
  @pytest.fixture(scope="class")
11
13
  def fetcher(self):
12
- return StealthyFetcher(auto_match=False)
14
+ return StealthyFetcher
13
15
 
14
16
  @pytest.fixture(scope="class")
15
17
  def urls(self, httpbin):
@@ -3,13 +3,15 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling.fetchers import AsyncFetcher
5
5
 
6
+ AsyncFetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  @pytest.mark.asyncio
9
11
  class TestAsyncFetcher:
10
12
  @pytest.fixture(scope="class")
11
13
  def fetcher(self):
12
- return AsyncFetcher(auto_match=True)
14
+ return AsyncFetcher
13
15
 
14
16
  @pytest.fixture(scope="class")
15
17
  def urls(self, httpbin):
@@ -3,12 +3,14 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling import PlayWrightFetcher
5
5
 
6
+ PlayWrightFetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  class TestPlayWrightFetcherAsync:
9
11
  @pytest.fixture
10
12
  def fetcher(self):
11
- return PlayWrightFetcher(auto_match=False)
13
+ return PlayWrightFetcher
12
14
 
13
15
  @pytest.fixture
14
16
  def urls(self, httpbin):
@@ -3,13 +3,15 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling import StealthyFetcher
5
5
 
6
+ StealthyFetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  class TestStealthyFetcher:
9
11
  @pytest.fixture(scope="class")
10
12
  def fetcher(self):
11
13
  """Fixture to create a StealthyFetcher instance for the entire test class"""
12
- return StealthyFetcher(auto_match=False)
14
+ return StealthyFetcher
13
15
 
14
16
  @pytest.fixture(autouse=True)
15
17
  def setup_urls(self, httpbin):
@@ -3,13 +3,15 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling import Fetcher
5
5
 
6
+ Fetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  class TestFetcher:
9
11
  @pytest.fixture(scope="class")
10
12
  def fetcher(self):
11
13
  """Fixture to create a Fetcher instance for the entire test class"""
12
- return Fetcher(auto_match=False)
14
+ return Fetcher
13
15
 
14
16
  @pytest.fixture(autouse=True)
15
17
  def setup_urls(self, httpbin):
@@ -3,6 +3,8 @@ import pytest_httpbin
3
3
 
4
4
  from scrapling import PlayWrightFetcher
5
5
 
6
+ PlayWrightFetcher.auto_match = True
7
+
6
8
 
7
9
  @pytest_httpbin.use_class_based_httpbin
8
10
  class TestPlayWrightFetcher:
@@ -10,7 +12,7 @@ class TestPlayWrightFetcher:
10
12
  @pytest.fixture(scope="class")
11
13
  def fetcher(self):
12
14
  """Fixture to create a StealthyFetcher instance for the entire test class"""
13
- return PlayWrightFetcher(auto_match=False)
15
+ return PlayWrightFetcher
14
16
 
15
17
  @pytest.fixture(autouse=True)
16
18
  def setup_urls(self, httpbin):