From c243c8aca5fe5155dd6476064fcf133aaf0a1939 Mon Sep 17 00:00:00 2001 From: ETM-Code <158038827+ETM-Code@users.noreply.github.com> Date: Sat, 30 May 2026 11:37:22 +0100 Subject: [PATCH 01/11] feat: add `--version` flag to the CLI - Add a `--version` flag to the main CLI group using click's `version_option` - Prints `Scrapling, version ` and exits, sourcing the version from `scrapling.__version__` - Add a CLI test asserting the flag's output Closes #299 --- scrapling/cli.py | 4 +++- tests/cli/test_cli.py | 9 ++++++++- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/scrapling/cli.py b/scrapling/cli.py index 47056d9..4b9eb86 100644 --- a/scrapling/cli.py +++ b/scrapling/cli.py @@ -2,6 +2,7 @@ from pathlib import Path from subprocess import check_output from sys import executable as python_executable +from scrapling import __version__ from scrapling.core.utils import log from scrapling.engines.toolbelt.custom import Response from scrapling.core.utils._shell import _CookieParser, _ParseHeaders @@ -10,7 +11,7 @@ from scrapling.core._types import List, Optional, Dict, Tuple, Any, Callable from orjson import loads as json_loads, JSONDecodeError try: - from click import command, option, Choice, group, argument + from click import command, option, Choice, group, argument, version_option 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" @@ -650,6 +651,7 @@ def stealthy_fetch( @group() +@version_option(version=__version__, prog_name="Scrapling") def main(): pass diff --git a/tests/cli/test_cli.py b/tests/cli/test_cli.py index 39345d0..642699d 100644 --- a/tests/cli/test_cli.py +++ b/tests/cli/test_cli.py @@ -4,8 +4,9 @@ from unittest.mock import patch, MagicMock import pytest_httpbin from scrapling.parser import Selector +from scrapling import __version__ from scrapling.cli import ( - shell, mcp, get, post, put, delete, fetch, stealthy_fetch + main, shell, mcp, get, post, put, delete, fetch, stealthy_fetch ) @@ -32,6 +33,12 @@ class TestCLI: def runner(self): return CliRunner() + def test_version_flag(self, runner): + """Test that the --version flag prints the Scrapling version and exits""" + result = runner.invoke(main, ['--version']) + assert result.exit_code == 0 + assert result.output.strip() == f'Scrapling, version {__version__}' + def test_shell_command(self, runner): """Test shell command""" with patch('scrapling.core.shell.CustomShell') as mock_shell: From 9e43062a63613d9785bd34226b4259181bc0a64f Mon Sep 17 00:00:00 2001 From: Evan Alferez Date: Mon, 1 Jun 2026 09:30:21 +0900 Subject: [PATCH 02/11] docs: use pyd4vinci/scrapling in remaining Docker examples (#282) PR #283 fixed the bare `scrapling` image name in docs/ai/mcp-server.md; the agent-skill MCP reference and CLI extract docs still used the unqualified name, which Docker resolves against the official library namespace and fails with pull access denied. --- agent-skill/Scrapling-Skill/references/mcp-server.md | 2 +- docs/cli/extract-commands.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/agent-skill/Scrapling-Skill/references/mcp-server.md b/agent-skill/Scrapling-Skill/references/mcp-server.md index 48a2d10..6aaa014 100644 --- a/agent-skill/Scrapling-Skill/references/mcp-server.md +++ b/agent-skill/Scrapling-Skill/references/mcp-server.md @@ -208,7 +208,7 @@ Docker alternative: ```bash docker pull pyd4vinci/scrapling -docker run -i --rm scrapling mcp +docker run -i --rm pyd4vinci/scrapling mcp ``` The MCP server name when registering with a client is `ScraplingServer`. The command is the path to the `scrapling` binary and the argument is `mcp`. \ No newline at end of file diff --git a/docs/cli/extract-commands.md b/docs/cli/extract-commands.md index 671cdcc..b3663c9 100644 --- a/docs/cli/extract-commands.md +++ b/docs/cli/extract-commands.md @@ -50,7 +50,7 @@ The extract command is a set of simple terminal tools that: scrapling extract get "https://example.com" content.txt # Or use the Docker image with something like this: - docker run -v $(pwd)/output:/output scrapling extract get "https://blog.example.com" /output/article.md + docker run -v $(pwd)/output:/output pyd4vinci/scrapling extract get "https://blog.example.com" /output/article.md ``` - **Extract Specific Content** From dbc6817f73655821c3fe9e06271b8426bef70892 Mon Sep 17 00:00:00 2001 From: Andrew Barnes Date: Mon, 1 Jun 2026 09:04:48 -0400 Subject: [PATCH 03/11] Fix CONTRIBUTING docs link --- CONTRIBUTING.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 3967c1d..c1ed65f 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -11,7 +11,7 @@ There are many ways to contribute to Scrapling. Here are some of them: - Report bugs and request features using the [GitHub issues](https://github.com/D4Vinci/Scrapling/issues). Please follow the issue template to help us resolve your issue quickly. - Blog about Scrapling. Tell the world how you’re using Scrapling. This will help newcomers with more examples and increase the Scrapling project's visibility. - Join the [Discord community](https://discord.gg/EMgGbDceNQ) and share your ideas on how to improve Scrapling. We’re always open to suggestions. -- If you are not a developer, perhaps you would like to help with translating the [documentation](https://github.com/D4Vinci/Scrapling/tree/docs)? +- If you are not a developer, perhaps you would like to help with translating the [documentation](https://github.com/D4Vinci/Scrapling/tree/dev/docs)? ## Making a Pull Request To ensure that your PR gets accepted, please make sure that your PR is based on the latest changes from the dev branch and that it satisfies the following requirements: From 6390c0af3d0a296ae895cd6a769dde8c3168fac6 Mon Sep 17 00:00:00 2001 From: Bortlesboat Date: Mon, 1 Jun 2026 21:30:16 -0400 Subject: [PATCH 04/11] fix: parse quoted charset values in content-type headers `ResponseFactory.__extract_browser_encoding` matched the charset with `charset=([\w-]+)`, which stops at a quote character. RFC 7231 permits the charset value to be a quoted-string (e.g. `content-type: text/html; charset="ISO-8859-1"`), so for any quoted charset the regex failed to match and the function silently fell back to the `utf-8` default. A page served as quoted ISO-8859-1 / windows-1252 / Shift_JIS would then be decoded as UTF-8, producing mojibake. Allow an optional surrounding quote in the pattern (`charset=["']?([\w-]+)`) so the value is captured without the quote. Unquoted headers are unaffected. The existing `content_type_map` fixture in tests/fetchers/test_utils.py was unused; add focused tests covering unquoted, quoted, and missing charsets. --- scrapling/engines/toolbelt/convertor.py | 2 +- tests/fetchers/test_utils.py | 27 +++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 1 deletion(-) diff --git a/scrapling/engines/toolbelt/convertor.py b/scrapling/engines/toolbelt/convertor.py index 8d624e0..cf303c8 100644 --- a/scrapling/engines/toolbelt/convertor.py +++ b/scrapling/engines/toolbelt/convertor.py @@ -10,7 +10,7 @@ from scrapling.core.utils import log from .custom import Response, StatusText from scrapling.core._types import Dict, List, Optional -__CHARSET_RE__ = re_compile(r"charset=([\w-]+)") +__CHARSET_RE__ = re_compile(r"""charset=["']?([\w-]+)""") class ResponseFactory: diff --git a/tests/fetchers/test_utils.py b/tests/fetchers/test_utils.py index 942835f..4679478 100644 --- a/tests/fetchers/test_utils.py +++ b/tests/fetchers/test_utils.py @@ -1,5 +1,6 @@ import pytest +from scrapling.engines.toolbelt.convertor import ResponseFactory from scrapling.engines.toolbelt.custom import StatusText, Response from scrapling.engines.toolbelt.navigation import ( construct_proxy_dict, @@ -139,6 +140,32 @@ def test_unknown_status_code(): assert StatusText.get(1000) == "Unknown Status Code" +# The private classmethod is name-mangled; resolve it once for the tests below. +_extract_encoding = getattr(ResponseFactory, "_ResponseFactory__extract_browser_encoding") + + +def test_browser_encoding_unquoted_charset(): + """A charset declared without quotes is returned verbatim.""" + assert _extract_encoding("text/html; charset=utf-8") == "utf-8" + assert _extract_encoding("text/html; charset=ISO-8859-1") == "ISO-8859-1" + assert _extract_encoding("text/html;charset=windows-1252") == "windows-1252" + + +def test_browser_encoding_quoted_charset(): + """A quoted charset value (RFC 7231 allows quoting) is unwrapped, not dropped.""" + assert _extract_encoding('text/html; charset="utf-8"') == "utf-8" + assert _extract_encoding('text/html; charset="ISO-8859-1"') == "ISO-8859-1" + assert _extract_encoding("text/html; charset='Shift_JIS'") == "Shift_JIS" + assert _extract_encoding('text/plain; charset="windows-1252"; boundary=x') == "windows-1252" + + +def test_browser_encoding_defaults_when_missing(): + """Fall back to the default when no charset is present or the header is empty.""" + assert _extract_encoding("text/html") == "utf-8" + assert _extract_encoding("") == "utf-8" + assert _extract_encoding(None) == "utf-8" + + class TestConstructProxyDict: """Test proxy dictionary construction""" From cd4cdc69e622c1e9f07a709cc7180a2ee6b6fd2a Mon Sep 17 00:00:00 2001 From: Mubashir Rahim Date: Thu, 4 Jun 2026 14:53:10 +0500 Subject: [PATCH 05/11] fix: prevent IndexError in adaptive relocation with auto_save When `css()`/`xpath()` are called with both `adaptive=True` and `auto_save=True`, the relocation branch guarded the re-save with `if elements is not None`. However `relocate()` returns an empty list (never `None`) when no candidate clears the `percentage` threshold, so the guard always passed and `self.save(elements[0], ...)` raised `IndexError: list index out of range`. This crashes exactly when adaptive resilience is needed most: the page structure changed enough that nothing matches above the threshold. Fix: use a truthiness check (`if elements and auto_save`) so the re-save is skipped when relocation yields nothing. The successful relocation path (which re-saves the relocated element) is unchanged. Added a regression test that fails before the fix (IndexError) and passes after. Co-Authored-By: Claude Opus 4.8 --- scrapling/parser.py | 2 +- tests/parser/test_adaptive.py | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/scrapling/parser.py b/scrapling/parser.py index 2b88af3..200cb43 100644 --- a/scrapling/parser.py +++ b/scrapling/parser.py @@ -671,7 +671,7 @@ class Selector(SelectorsGeneration): element_data = self.retrieve(identifier or selector) if element_data: elements = self.relocate(element_data, percentage) - if elements is not None and auto_save: + if elements and auto_save: self.save(elements[0], identifier or selector) return self.__handle_elements(elements) diff --git a/tests/parser/test_adaptive.py b/tests/parser/test_adaptive.py index 8d40f77..85881d1 100644 --- a/tests/parser/test_adaptive.py +++ b/tests/parser/test_adaptive.py @@ -56,6 +56,32 @@ class TestParserAdaptive: assert relocated[0].has_class("new-class") assert relocated[0].css(".new-description")[0].text == "Description 1" + def test_relocation_auto_save_no_match_above_threshold(self): + """Adaptive relocation with `auto_save=True` must not crash when no element + clears the `percentage` threshold (relocate() returns an empty list).""" + original_html = """ +
+
+

Widget

+

A widget

+
+
+ """ + # Unrelated structure so nothing can match a high threshold + changed_html = "totally unrelated content" + + old_page = Selector(original_html, url="example.com", adaptive=True) + new_page = Selector(changed_html, url="example.com", adaptive=True) + + old_page.css("#target", identifier="target", auto_save=True) + + # Before the fix this raised `IndexError: list index out of range` because the + # guard checked `elements is not None` but relocate() returns [] (never None). + result = new_page.css( + "#target", identifier="target", adaptive=True, auto_save=True, percentage=95 + ) + assert list(result) == [] + @pytest.mark.asyncio async def test_element_relocation_async(self): """Test relocating element after structure change in async mode""" From f0db3d7d1405544fdf5ba6eaed1791d50518d73a Mon Sep 17 00:00:00 2001 From: Ahmed Elshahat Date: Sun, 7 Jun 2026 04:24:12 +0300 Subject: [PATCH 06/11] fix(spiders): use os.replace for atomic checkpoint/cache writes on Windows CheckpointManager.save() and ResponseCacheManager.put() write to a temp file and then move it into place with Path.rename(). On Windows, os.rename cannot overwrite an existing destination and raises FileExistsError (WinError 183), so every write after the first one fails: checkpoint saving raises and breaks resume, while the development response cache swallows the error and keeps returning the stale entry. Path.replace() (os.replace) overwrites the destination atomically on every platform and behaves identically to rename() on POSIX, so this is a no-op on Linux and macOS and only fixes the broken overwrite on Windows. Add a regression test for the cache overwrite path; the checkpoint overwrite is already covered by test_multiple_saves_overwrite. --- scrapling/spiders/cache.py | 2 +- scrapling/spiders/checkpoint.py | 2 +- tests/spiders/test_cache.py | 21 +++++++++++++++++++++ 3 files changed, 23 insertions(+), 2 deletions(-) diff --git a/scrapling/spiders/cache.py b/scrapling/spiders/cache.py index 40d39d3..0305aef 100644 --- a/scrapling/spiders/cache.py +++ b/scrapling/spiders/cache.py @@ -64,7 +64,7 @@ class ResponseCacheManager: async with await anyio.open_file(temp_path, "wb") as f: await f.write(serialized) - await temp_path.rename(self._cache_path(fingerprint)) + await temp_path.replace(self._cache_path(fingerprint)) except Exception as e: if await temp_path.exists(): await temp_path.unlink() diff --git a/scrapling/spiders/checkpoint.py b/scrapling/spiders/checkpoint.py index 25de362..95515bf 100644 --- a/scrapling/spiders/checkpoint.py +++ b/scrapling/spiders/checkpoint.py @@ -50,7 +50,7 @@ class CheckpointManager: async with await anyio.open_file(temp_path, "wb") as f: await f.write(serialized) - await temp_path.rename(self._checkpoint_path) + await temp_path.replace(self._checkpoint_path) log.info(f"Checkpoint saved: {len(data.requests)} requests, {len(data.seen)} seen URLs") except Exception as e: diff --git a/tests/spiders/test_cache.py b/tests/spiders/test_cache.py index fc9bc59..eb1b04b 100644 --- a/tests/spiders/test_cache.py +++ b/tests/spiders/test_cache.py @@ -49,6 +49,27 @@ class TestResponseCacheManager: assert dict(restored.headers) == dict(original.headers) assert dict(restored.request_headers) == dict(original.request_headers) + @pytest.mark.anyio + async def test_put_overwrites_existing_entry(self): + """Re-caching the same fingerprint must replace the stored response. + + Regression test for a Windows-only failure: ``Path.rename`` cannot + overwrite an existing destination on Windows (raising ``WinError 183``), + so the second ``put`` was caught by the error handler, the temp file was + removed, and ``get`` kept returning the stale body. ``Path.replace`` + overwrites atomically on every platform. + """ + with tempfile.TemporaryDirectory() as tmpdir: + cache = ResponseCacheManager(tmpdir) + fp = b"\x05" * 20 + + await cache.put(fp, _make_response(body=b"first"), "GET") + await cache.put(fp, _make_response(body=b"second"), "GET") + + restored = await cache.get(fp) + assert restored is not None + assert restored.body == b"second" + @pytest.mark.anyio async def test_get_cache_miss(self): with tempfile.TemporaryDirectory() as tmpdir: From 9c0c857245726352a8502b1e4822a444ade96543 Mon Sep 17 00:00:00 2001 From: Karim shoair Date: Sun, 7 Jun 2026 15:51:10 +0300 Subject: [PATCH 07/11] fix(parser): use max of both attribute counts in similarity scoring denominator Candidates with fewer attributes than the original got inflated scores because the denominator counted candidate attributes only, while the extra-attributes penalty direction worked as intended. Using `max()` on both counts fixes the inflation while keeping the penalty. Closes #322 --- scrapling/parser.py | 4 ++- tests/parser/test_find_similar_advanced.py | 37 ++++++++++++++++++---- 2 files changed, 34 insertions(+), 7 deletions(-) diff --git a/scrapling/parser.py b/scrapling/parser.py index 2b88af3..a075f2b 100644 --- a/scrapling/parser.py +++ b/scrapling/parser.py @@ -991,7 +991,9 @@ class Selector(SelectorsGeneration): SequenceMatcher(None, v, candidate_attributes.get(k, "")).ratio() for k, v in original_attributes.items() ) - checks += len(candidate_attributes) + # Using `max` so candidates with extra attributes are penalized and candidates + # with fewer attributes don't get inflated scores from a smaller denominator + checks += max(len(original_attributes), len(candidate_attributes)) else: if not candidate_attributes: # Both don't have attributes, this must mean something diff --git a/tests/parser/test_find_similar_advanced.py b/tests/parser/test_find_similar_advanced.py index 099b0dd..95e1e69 100644 --- a/tests/parser/test_find_similar_advanced.py +++ b/tests/parser/test_find_similar_advanced.py @@ -2,6 +2,7 @@ Tests for Selector.find_similar() with non-default parameters. Target file: tests/parser/test_general.py (append to TestSimilarElements class) """ + import pytest from scrapling import Selector @@ -61,14 +62,10 @@ class TestFindSimilarAdvanced: first = product_page.css("div.product")[0] # Ignore both data-price and data-category → only class matters → all 3 divs match ignore_all_data = first.find_similar( - similarity_threshold=0.2, - ignore_attributes=["data-price", "data-category"] + similarity_threshold=0.2, ignore_attributes=["data-price", "data-category"] ) # Ignore nothing → data-category difference (fruit vs veggie) may reduce matches - ignore_nothing = first.find_similar( - similarity_threshold=0.9, - ignore_attributes=[] - ) + ignore_nothing = first.find_similar(similarity_threshold=0.9, ignore_attributes=[]) assert len(ignore_all_data) >= len(ignore_nothing) def test_find_similar_on_text_node_returns_empty(self, product_page): @@ -76,3 +73,31 @@ class TestFindSimilarAdvanced: text_node = product_page.css(".name::text")[0] result = text_node.find_similar() assert len(result) == 0 + + def test_find_similar_attribute_count_mismatch_scoring(self): + """The similarity denominator uses max() of both attribute counts, so candidates + with fewer attributes don't get inflated scores and candidates with extra + attributes stay penalized.""" + html = """ + +
+
Alpha
+
Beta
+
Gamma
+
Delta
+
+ + """ + page = Selector(html, adaptive=False) + first = page.css("div.card")[0] # Alpha + + similar = first.find_similar(similarity_threshold=0.9, ignore_attributes=[]) + texts = {el.text for el in similar} + + # An exact attribute match must pass + assert "Delta" in texts + # Beta matches 1 of Alpha's 4 attributes; the old denominator counted candidate + # attributes only, inflating it to a perfect score (1.0 / 1) + assert "Beta" not in texts + # Gamma's extra attribute dilutes the score (4.0 / 5) - the intentional penalty + assert "Gamma" not in texts From 4ced6e4ac26893304464f6368454a80830c3263d Mon Sep 17 00:00:00 2001 From: Karim shoair Date: Sun, 7 Jun 2026 16:16:23 +0300 Subject: [PATCH 08/11] build: pump up version, browsers and deps --- .github/workflows/tests.yml | 2 +- agent-skill/Scrapling-Skill.zip | Bin 90018 -> 90020 bytes agent-skill/Scrapling-Skill/SKILL.md | 4 ++-- .../Scrapling-Skill/examples/README.md | 2 +- pyproject.toml | 8 ++++---- scrapling/__init__.py | 2 +- scrapling/engines/toolbelt/fingerprints.py | 4 ++-- server.json | 4 ++-- setup.cfg | 2 +- tests/requirements.txt | 2 +- tox.ini | 4 ++-- 11 files changed, 17 insertions(+), 17 deletions(-) diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index f82605d..930d0a0 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -73,7 +73,7 @@ jobs: - name: Install all browsers dependencies run: | python3 -m pip install --upgrade pip - python3 -m pip install playwright==1.59.0 patchright==1.59.1 + python3 -m pip install playwright==1.60.0 patchright==1.60.1 - name: Get Playwright version id: playwright-version diff --git a/agent-skill/Scrapling-Skill.zip b/agent-skill/Scrapling-Skill.zip index 22fbb3231c28ed74331a39fbddbe65c71e15ae82..1a8d15b54cc8f92b9465e6ece763689a08e89e50 100644 GIT binary patch delta 9276 zcmZ{KbySpF_y0UI)X*_VBi#bh4N}sb(gKo#G$JrGNP9;Z5RgW?Q$SLXZV-_M=}wXO zf!_PR_g(Azd)7KLv+L}A_C9;hAD<_y1vRGy6-PrEf&v5GJgOkbY9M=Q&cE_OKwMhx`~W)K^YZyZS_yZEaA)$G@+`<7=V zp7$+UAX4{Nj4O(H`uO#{mM?Z8_qi!?MU#z-D#~4Gk92JMG7UN0i><#Y!kWfk7N`o` zBf2c@41EWWGUiMmrof8%$?r)-^3fQYoZurQn49G6W>>PFd!h1rdED_YIW{atH9@&& z%4vnyQeU-tU?L@NRkTn`)m3{dMpwejF&9^Gos z0O$rLWtHMsW(;E!^QL^-VBcua3z!};oh~71bDJJr7*xYG{`qPipM# zoIK1btk?p@AWn~-v{N-!qnjy85cP|pF#eV*X4R8;qnOKBmhxg0*M@^eJt-W9hnFpaZh&|%>Y`wt$!%@{7wFTa z!QmJqe?w*;Q4VQ>ZWh&RK!+(N?H)g7<|-jsUC$fk12&qBS${ zawf~CYaiE0x9#e)*2w7>EGOk5Hm%+~GRYnSk-7vL_Be@$)~63rO6DWh0^l~4jpc{- zwS+%m!%iW+E0hUYDxH*X$H__y3z~*|d)%r$ZOj`$!>=+Tb)n?h=$q0fqG^`+V#9E) z)UB-VpsO_Vd~DOCXgz9Do|#B2Xr~Z*N0c^RQULEl;t?6t98I=D#DZ_UTcN*xEIClI z6^*el(J4OfZ2x?*Po}oA3a+*W>sG{;!K7jML8pu(^?Fu8oJVUrP$6QmRl=UnC~ewN z0O>hVfHE;8Kp8~Yg=yq2QpQ*;0{Q;RPZW#lne9ouv#X+nwzTX7BMwR!?A5pt(FTuO zAoh^cJ(VA?8GSxZlP?6?RqSk=sl}?9^6``1iLE`Y>74m-qm1R^kO0di<)z=R^&c2e z`4em$V=r3C`3V`sY;f~PDZ^LXG+Zi5n+WMbSWgAaN|(Um32ADUp2kTL0X56|Ty1G6 z84))2NvF6g{T+0Pt?>4j*23(GLC$kCC`3=_$^ot2(}En zhy3B<*jLv(JsW*>&P?|^4`!yy;^xGN_u}UK_n zJ`Ig4+>r??@Fog5P>N?;iqX{*^WZGb?aY7Qtz0=DRWZ>9Jqhrig{>0`mp0%2fnhN{ z0>wQp$E)bVBiw1gx$Z5MqJg7kO8Ey*tD>2rQuL5~C^MUIxqfobhJ{V7j>wSD4_dVG zU?gbxElr2jCPwqs0Wrc2iyk;aAhD>ac<(Ksbq2VgaqK7ds5#aksgYj&;$12Kb!JFjEFTffNtKaaSq)pV*=$D$Ve1TnECVh`_XlhcA%z>-r<(`w1OtUVuN>iqFOu+E+fuhWI^06m7D>SA)CXhPyN|=n(MdZI zc0Y~ufuqBLjjFQu&Dr5z5PdHStp672cN%mf8!w69n9p_49ec*99yc zWKm`F&4om$&smZ*qC;4iV;gF)v>D(ia=Ni@+HYH6E*PXyJlb{9b*Onx(P!{)OY;4T zI}h^+gQ?mA2w&irwW|2T%w18?d_fJL6dj+mURr0faCgaCO>2Q|?EAD1H{3y0)9pD0 z4WvOXSwaJm1Wo<@yRX1MaG1VgkaBOr?6WDstNR$xZ&%? z@{7&8TJ4d zlZ(Us^ugK{(+IZKLL7qEmd}df56=P()aCjx#Dw=Pra+`VF5A%o)pS)^bx8ZZhe`k^ zrUH2%!v$%~9OQuVOCvWDf&sl(Iehg6Afn`Q22sU$&egF5@2;z@ufu2jmEH;I5OLRt zt>6qCsH67terRSftWFdulIFqu#%r>(5gqhl?*d79 z|IoT$gR&xiAp4}eTw-FXfmWt>W-t*p_&r%BapQ{v;P zre?Tb0D{lTp<8^RIYQnRKGv`QOdr3vR&>l`{$sUa(F;rN_>fHaGx*Ou#jVD{aZ#qB zT-)}cBT>Ajty5OKRWbkb^#hW(yAqd^#XL{?HUD}6ro7DBmUr(np0bT-x<|l_YZk$o zzx32QBs==^)(#Oy%zb&hcFHzQm)@W93LPA@NZBgN&lSBEXetyjw$9C`KIcl$`fyew zbOkPbMsXC|^f-3C;6gO_!b3}Chim|OQQ-gycFB1Xh6T=pvog_(Qh%?=4*0C5_lczg zrM+XSGQoQz(pJfY2mWo7{354{M27uU&$qVaJo>PYjrs z65=JK`B+vtMsPkSFlv`-<2PLL043*d_`Pzk8_ViRq~5Ec9&n-Wr17w~>^3Q3v1E-8 zG-Ra&eB6(;#HD35IB(*9$Rg#gD6zAr25mO;5-F=4jK^mF(ICM%2aZfVG1KI1f{t_d zY!9af*C`JcPHmRdHBzJIOEA9wlpM0tYVWq)Dh)dha)2j}3uE4^RZb9dONgh;povaaXtL z4ZqYZ57AN2A-6$>S4wXsJKvAEdXN0)`DT>~(xtWHXAG7SPhq1NFo~x$t;g+87IbPR z+Cl=pyTVg@Rm<=F#Z6HN^L}h76cYX{ppyPH_?u{{M}N(k-`Q%FQ)mB>%;ASwXi48? z=sOZ?m8V>+1$(A^=0uHJH!<&8M8)qJKK%>nJ3hEzZ+){50>X|*N zsbYNnCAwCpZsA*sG4UuPo9FBv`(G}!n1yMWfwVm{#SUemgViRX2GH?TiK$gjb&;^5 zGN%L|@)}q5lZ+B=v+uDt5yZkTORWy7NThmL1~2(%JDgUSDCl@}q*+<9_a2p{J1DQ( zNgOZ2*Zp%xeJd6}9?K30Ds$j(-E0$25*o&cb-uTyMxKYL3-z=1J)x?bu8P)^n@y_< zefzfQ$(LPjOSC2|D(Hf2$w2;Jn`oh)vY*npnvu%fr9FJ*oSHGpsMDIJ8p3aSY8}ky z*EtQK$)C}N4)fX1Gd%yB)?C5@cxyZ^wR^eL_JrVLczVdYio)vt$G!&U zVH5Q-`(qPe)Bf_)QoT@x2P?)OKq$G-GEpZ68X_&!AXbs;t|L$im09Pf96s)=1_qC6 zjS`uLV$@J7@#(A!Dgu&wFQo_u12^)&4SyW(YsS z2&Z3+%6&k^)ApB%KJjzLdkQ_<(QMVmqfcWc*bfEMxPw0FzDhP%WUy@pGNPjfr*c60 zY!b`%HWE%A;bVGGXG^+6k+g45?X>jQa1Tvbp0GZ!4>jkH^EGB<)M3;o{8rP8aQn-=}`Tvz-xF^T7#z zQGw5~uQKm5&GMlGbTOt+#AmClyAnF6BtrREF;PZR3FQ-fueEB#i{kC~d_G@+H{;`v zgkl=fK1LkH7mLSqiJOaQ&1Gc!pc6C`5$sAucb}hS#EpR-yz(2@a^Cm?D-Uglb|=+#Y|U0tJgBIvj4Q3)#Dq_gQq$~@CRrEe-MftT_V`i?!%=F?_1ND1nr1X| zkGuJ^&(nQZe9#Q&bS}wd%>igbz9PX8OYu)V=QKXs79Xuo|nyA?lmB_+-#^q~#y zeq=b_c~gCI%BWhK<@+yBc*7Yv2qZyKsA8$;Ib?vmnFJS2=uihR%*Z8;obp z6pu4TnD@L~U6Sq^BurzITL)i1v~!T6?KBkMh1rSS8@cHbrk?fxa82!P8+me1yxUX9 zcf`6)THmfEWS`Ydf1;ak|Do)P=U~RzF~lW=vSC@NJgK?MqtR;$O3~(3Qapj_+7w+; zh^7d#Fj{A<|E3*Iz10c+Zck&aY3Y2%1WuXWS|a%6G*j^Wyv*d(tPy^7eNB)`KRFv0 znn%1HT=Hh#*+F7`h`^R+V7gSS?|?M9Hk{H(P+4`dWv!N@P)6MMelVT_%hsl`O8AI8 z9KXk!=!(&F&vt$yP@7E(qnBXWUP%^ftcK1q7rmZsqm^${-=^bAbE zzq-sx{2+vRM10J;68O>CDU3$Ep zH!AogZbw7sbDi!*asA4;r&cdX(rfegmGC{Fm>q9o!PMIO~+g+Qk17oa)iPYgIN`VXa*5e^i@?!l77B z7s9F4!tc=|hqvS>^B~mYl)P_yWU$j>gvx@rhRWmDtC}%bORZR1%3~B%@r%cYWZ0P5 zK|XFFA!j1l-cA96xF{xT=$`vE(bx|%t?lfkL~qKBHhFXxYWU%fDqbh?ezm1X)BZ~= zV^rKGeZEOBcRb9a)a3#w{K$CKdy<`@OME>x8-dhuY*$0KB^G4TBp4^2o6jxZM?0=M zAj13@-}4wdgUgjuodA;|T#2R0I@^`y9S0#Z%_3nQZs}?CyD$eVjZ})N@Q>`wUa`Ms z`Ka3u`f&mcA3ufrM-RNSf0c#*EE-)Gt!@7c^m9Zk>XvuJ#+ql zUckN>20J`M*U7Qul+RGFB^3>%pa`a}@Pt`Dqe2G$`o6d=@!5&C(H+bYlzpw&^k&WH zWw&GCQJyUqnz}@z$?>-y0$EGFm`io5A@l7rDWXOO^84PUa4{=Myt!vqgs(hGcLFFw zeS(@N1Uj!@OWqaI;S(+Ml$-MRvUY*mteOOUWI|k$jvGezO=JyUwXB}@~ zTq1>3hx3A)zHrf8%GVUGAbIzf3Pqc4K*Mqaxuk~jW)0GcG|7b6XKwr~GM3iOtqJT5 zJt|r(1_@JY$G$H!Pz{F|o*O%;yjh2x(P+w_qBgajy``2~SuEZG&Uw>byjbVd>22&b zznVQU^C{6b92VfZaU+k^dzVe{(3qlij50MUs_2`5BwWP#WN$F;P=C2zbP==JIKi7r z=j*7F%GDF9xhyQN_V_K8WwT|v`b@vnO*!5i_1P%XGrW4{V@B>D_t#rnk(}lduAC*T zt=&D3h#iXT(XU({uL%|(d|~@&uG*B>8q2*Sxa8pAUPLQXIM5yOW_HF?AVKxyQw*_A zWZW6Eq78f?&%FguT(uU?Y5W*e)e}0t;J&nhk!s&b^wCJyQ6Wd7Y0Okv^7xf|xA?m* z&ygT?0tw$s(GT}+pG#~!I?J3Os1{r|?Njbu_}cLpM{ERB*>30y#R@Fw3ehWrYm_Y3X1}`Y~t~L=8%jlTS1t@{9DR)r6bOr*p8x^Y#;l#ab$1blQN@EW!D&JGPoE{6Xd&Fh4J^+}x){GO(vqq+(!e z?91^+^{uV>XNn4CmdVSBAI@i@yy)-wy;%RkUPCuM90O$P`Gm)pJP1kZerH;WxgX$w zo^ZVgSGTzeW+9l}+Z~om3fxwyYHzm8OQ#9=F60_ z8oW?tq+Dffj=y?=T*Q^KAqYgsQiY~tCzi3MzN=@=Q=h?n0=(cHI#Q0W9Y|gIv9Siv zHCmEp?8uj$4Y01DFK%yDwADR8-?=VSxuGg^whWbkP!`i#msA+K)U)2ZPh zYu}#?`cTK`-K)1~?XPp)TNfs+ogA!}1z$enF|uRLZK!VgUuEmTzC^Sl3Il<}@)mQCL1_ zdMk&k{Uo<*0kE3f0??36;+)6axRTyOqwgP3=X@StEpUyzqSgY$ee zdO)$rILXBbHKjx^f;A^gei6+TtddxZdzic`?Y`ain$hd06K5SsP8H4$X<0cT-!s`) zIui%HFz0fSF8cQABX_HVkNlCr1=8C$fQB+U#$>Mzn*t>Wlxze7{SP!{{2Mp>`-2`t z12Qv14AAgn{exEh!Maol4W6}rn{y9Sq`Ean$B+%Veu;3THAE@uLA9^yp$&$h-~IX< z7(;$g0SFP3jKzOrZO;+IO(<2TOq9^yfEzKlD)t?ecJepaR^`O)MPTdMtmko9E6n2_ z(I#A{^8L-kSBz9$$eDdM0d8+U*%^@B>L(Y%go~5sPEh$ao3!iOIbL)>zH4tGT zTmJ935g+97s}kg#{|y{IMEKCckd2H0>^Jy_{HO^qBlgv>s%js@!T)3IPm5pGpd^j* zZ{{6th=`D5L&j?Zrthxy+B4ARK?%W= zHW_p%i-%0S)CGI0*6ZQVJWl8i=0-QnhnIZeP(Xo(%o5M>M=>q-z2wnP(j4}Gsbq&X zaDm4#=!}!!HX+^@&1dzsQDi@wQ_5YHrq6fxny2m@EN->$ndBPVND8JMtPTt1^$NkY z`Z1v7V?9ckRvbC3X%<0%{=5+@W|Gur-IFmTE?g%62|y+y(|NDl_4W9U>$4A#d0t{u zct@x5T4;Uz6vkU&$Nl_>J;nDU+#?|CXL0@XKH1$VhmXSD7;MqC z9-}>SG>$-3GV~M7;ZJ4F%h@sNs9xA9cu=>qn0qGvS2*wT`>6coP7&`@2e&Kw%a%EL zN-xp-)I(2?ErOin6*?_lyva!fFAy!L`IDgsSTP-jy*w5JR?wxy5D;MIBPlSdz$S0g|V{n_E;{8-TF41$g zS?QoPQ|Ccpy_Nd>XXOmuH!IEJ+-14w21)lx)*qH{j1;TQPObEI6ep}?XpR)^(goqq zXDa28K$X{ry5o|?r`?VlY@};f*a|<eRm&Oy_74i&h1Fbj17`YT)t$CF~k)4X~$Zqa*3+2vShgnX^Q z|ILMDPfjB;K)Qh4!f%jNJK|6^NEH5=WFMNi`6G8XP_HlN9Aa4)N2@oD!89S9PpZ{v zdt`cxtdO=|>p=s$!^6A7&0bJi5jKgYEzS zGpEW)TNw4{kF}Ah#WkBvb?@@8%zJOA$~bx*LER$^aM!f!)4g@cSJDq>2(?@IQjP zv3$2jof4ozdN(EhZE-6wz8mXE3S~h4|CHWMY2-^~K=aOj-GDM60LHlu!1zD25s9w` zXmb4@p%`Cqo4?b$^`3pZctNChf&6}Q0;Q1gYJd{Toe^?Q4Pb+i$bb+B&Xjj~MsleG z(qL~H?eoR z&;clr^BRCMI9(q3M){VweYpY)F)vS!bkqbMg4G}2sZb&tH35BahvI)!EWw#deX?y60%1F!?$NOc{+4cxB#C$mo(5Hjg}$52F`-4XaccLWnsQy(vKTA^VAc?6{D0NOOZ*RsXC% zjOHv#p*ltLr>y!$w`Ki)^p8F!5@~dMn&#s_s&~DFZwx3y0x$sNA_KsUjJ>0b zp}_Bu?!>9k+iL&5A(AElE~Ja$x1#bNzm+DpezO_>t9{#;st_W{zc(|LyuB0grniSY jko>K4*O_{d#m9fkITQfO+j|B@#+m`RXt%9-dzb$o+kd`l delta 9036 zcmZvC1yq#V7cbw?-64&X(nxosgmkxbBa%`>NJ|I9Idz3~BGgo~CQt*uCv)vKaUSIilkQE5u2FOpwbuXWLnX|801DovK)LC{&cYuCLoNbTPF- z2kenFP*`JWmB-uG?YgW5WoLkC;cpa?9J_E;lD6o)XLrwf_q^trO4%!Ah>A|WDW4eaD4J6SV%&OKC7+K?mHRj80McBIC z?4J@v!^zjMSR&jknO#tA%+j^GqUd+Ef1HiFG(O3QdY)hA@RWZCD$HL0>OdhI`&{LG zPco)8Drk1^gQ#8xYAAK4R}P!Kahat{_;BZreh;e~E34*fUGIsql!gQMr%|bf>>t3G zI5lhobMa3Lq=!n7R=+M26VE=&OzKxGMIjhSLbEniD1Vjh{Q?J4&Y`x(9MAg3DDx*j z&Kdaj*ZbS+w%cPmQ@@MHMTF8H+T1+zIMkUsP3)EyWpNbL&i%I+dY!K-=A}1=ii@)u zUb=6{biK`1>q?{S)8+kE4{syxktX#41Fvl`KMW<}hlBFrYz?T@;Uv8&rTKNps?YR) zq(6U$=fbfhp((WOX_iX%rl7ivpfnl2iTjy|S2Z{}%$Z%N&~QLY?$#3_TqKH5Q#>mLHK^7&@v%jkQ=wY=^T&gsQ?FgC9=fAAfk$|l z_^fdm;eNH0?ewm%-iQhsHb0gg?hi3=(@Gx?opW6Ekq@z9P8^8SWz0Rat$YX1hnoNm zMJbQ?rKOPQ45<*MTrZ{{NMj9HF~oE>skRTiW_Y_N9qi%rt+Yy%eAR_6!8Wgfu-Tj9i!C}dd3WMEsE3F>$F zlS;yjya)_2cxG;E40b9~%ZqGpPtVJKKS1qa`ic_Mu!T*r{CFIyB6AjvloY9xPOz}Y z?g>S8BZD!Bz^Z^b%4+?E-0mgnqjaKY6Io5~^u+aZ%ZX6X$Y?}IcN>a|;bXySh8#j1 z@=Q1_hFPnl&y$AHEF)-&O287u(Od_pFy@Ee6U7SVy*dTWAup|S!F#b6iLD>G1gnQKd@hj4CBen2Ve9>ZA`BDt+3Jger!U>DV<~EC;rY}={0kAJi6E^!tTlOS% zU{A3`by)Lpzx<$#Qua#OyMFA-tY&E^AG|bdq(G!HgVbDJzg#YzwowtZcI0c;u5hk? zT*M+~ME{TQKKr#023Tc7igYYCPqXl^U`%0T*T(cDBwJ~ca$-ffz}U`MvFr!wD9#%B zj$3FBmq-b8ZKBrfV&EOm;g?yRJRgu`ExBN0NGVfsV~mVlv{7#;@OBFnVdEJ?wjK`p z*~%K%&K(TBFDj}PijNh)mhr(`ChK8{7ZG~+7c9_KK4y6x)9=z2&pthE5lG_VgZ3Wm z+O}Kg7~~gcRsyu?WV6FJYbTq#YZdDJujzA;FLXvkLO8V9?J>DS zS*^+@p-&iBHuRmYk@4UK*ez%x)WXrhWVuNi7zWwaa4yku8216?TZv1BsDUrHZ;UFx zKEXw=&}5YP>alJS)9(JP6^WF5r=OicHr>+gc#Vwz~wOY;aX>TL<=9htVr zR0o1?Av>qV@67v1le*3Scztuv<8W#7dJ>YLiPDll(>jt0TBF}?)7C{Q8yUH{T;=c; zvF1~%jy7p__70TxP~cH>b#4S_jru_Racdi0Wr`Q)?C`VXlX{x%vNl*hst>E}^Fju& z9z4?biytOe%IaD&-G$M7dF|_adz$vz`W1r=jD;c8C^%@IWRpmwDi99A!Df*`NqAa~ z|EU|FXs;3XroT#>9*mkN9TYbG9L)@sst;=CW;W@5qe!;#h)u1Y*pNREvwVwlBovWC z-(kIt(QVBq4aM}$Pf-WSfz04`8nvr z(Jueyp0L5EVf|bYa}l2!y7^UgM;RN=lRmBZ@;hdjyrsP&&*p6&&?#Hdhmk@ zJD|ufBX~bX=B*A@ue^sr+OiIjHD`TL^hc&kxOhekej651jgz)~QCD)nNCC&5y4;Rx zqaj7diJ&ju;tgfOshfg6gE@p%F@9JK|2kYk{d#<^5~8ktzNK_VELV+;v)otvyK*P^ z^{><2)g8#$$-x3^n+Z4=P1Z|}@L4_?(IyX>I$fY6mPwN+C<6JciN8mR)JE9qaOi5% zD?b+(l{hAeV6Bt4-rFH&^(?of-`zFlXyYLsV5Mohopx9SAB#IQ0~^mpi8M=e>sVGZ zQfPqimPyn5)IqB8@L+uU$@=K$*y&O(B&gl#Q5?p~KTKQwK-q1zG!8s3tGqFH^RsS@y zU=#G$Lp7*lc<4UpOsaJwNw8CD{~&}FU2>NaNsc={n=nz&TJPjk%SA--FL>%b|DoTrNE)=;b z4Hj{qd7G@@R0?BbD#(=>Exa*{PE{j1AneeK9tf5*ZZd?~>C4>67M;FFxsFuZ$o9}Q z-rvF*r5mjOzIVM@wk}U`PI%Z35o?}_MXK`IyESi#68`l?& zN}uytTi&7&4uVNH<-Xr6NL=dsVeMFpJLNlS?0&5cUTYarmYR7k-<^{LCWWYnSSM^VY zmE=Bq&mk|owSRM3KNR5NjoR+m#AkX|sghZTC4`2oMBxZNg}P2Np zJBBy8zCY3!Ug=TK2~yhH@Ax^$R?tPwjL8ab=k9k^s2}u-i|BPCbYDIw+ze&oig+sA zZ_qp~8HPA_KY27rNKIOt=ljWvwPt9o!>e%tuRZEBs zR;%G$c)8K{2;#NQb+j`<$!K(U_1q^fxmDdI$ATTf>XqGMlMR?-^;)o>Tko(OFJDiB zku`J@2q9NHFUs1m;xeUMj5LznyP`c#bDVxZ%dD!c?46~I{(|6bm>fi^HSZO$w7)Wc zIfO$&iQ%Q)*k?KSdQGz?UC_ZHu{x62+or&je}NtHy}uw!_W~kNq3}~BAO7=rG$!PW zyy6!*@Cu8D#awOqUM^5_QiPjllG1P$;}5KE=@8roAQsqRM+3vJN^cX0Y%TIOVGFLUPh8s4I=ea)1{g$&{iq53wh zR`^ve_%-cl25)OGU(6~^;Z+Fs;Bm;ya5vh5l}vLjUNq_SdFW&I0a!Iru1uMd;qF$s zC7lkBAV})J@<;B9!{@vz_n?2~`f9Y@jaGta z-*e)Jq5Aohax^Jg-2@v)&O}@?8$Vukob^zDvQDhX5GTDvj0RHWu0U1OHKtL;=;iDI zm(HO$F<`>-ltX+{!sUGJ(H@CeN|m&%81}EPm zPQKh%KoO;J4}Cc`+Eks@jY^ds+QK$%|GW@en&bl03Ja}K9 zZHSzzN=1Dv0M-fmbfa$ef-`BnS8g|Y-97r-`J0Zcnu>AvOo;(|-LZKw<7Y~JJK?*u ze75i=L=uwP*i0;2sjG(l)79CF@92#vEALd1cZkLtbP{RSP*aIBoSV>2O&nl-_=a()zXClw8ZXdg5>CS(uA0JL?-DKl%^mS97 z9-BccjS@S(bP%6pi8?*L47ZZqlw6OSZ)RYy-*a}W`B7~@k!TLA+e)>If)7m8YB2Mi zftX|3OLs)iG9+bixKwt4nR9&;_7FUZ$+&4;2gOX251pVw>TlQ#c#ie5aM`2EdwoUk zOxPv$K#=9($I(*GG!`$fefq`l{M7IHXa?qk=;zfOMjpJY@5pzfzA9Yzl#nAD+YsAC z>@mbX`ES%<){n{e3tGF5c|5@sD2n`Vx8a>3xP@g6?UWve6rZs^Ivoy1`N+TrRAp;_ zV8a#N;?*1ZNxM^)e^TKJA3Jr3w4WSAGaK+hG0}E;Z;!fh^}Q#Z22IA_OHEk|iA2Qo zo(J$(%8djG7zxJ~PEH|M-=W>m5!058=Do<|_OEN%=s;GBpgH+;I`$kaMHY&hvt`Up zwdP474L`O?nl@@r%@f+1OX}d3js|icC%=!DK{brBXV-tmbbm)vKckrpro?I7by}s_nr0FK1 zI(Ve56|h^mTfkoVE+b2l1ZQGr$T*GbsI<7#V9u2`u|@F>%O$wr zeq*1&5Y(l}JqW>nE~8o=;-g=@sc|!yCAM>zUBKXi+-R~dolfmxwT z61(}n-cs=g;FciVm4@ZEEM=|F!)xwEl6F!u(Dxa$@5Y*lwN777@AXIHAl`fn_Br5j zlZ~lD7QGcteEY&9s)^p7 z0Td%eI5$_(bGvgK?L1fx+BEIPp*tv=@e+54ro56nV_Ef*(n`P@cBpQTTs~x!lJNK6`$(m>@DUJq<=aVck`@i$Wk?;8vJbvSsP@z*NthP$SJ|TC%nlvhMO0WVWd&}?N51#dm|h$M+K*f z=?KBW)QPa~#$eBjT7g`G}@F2A=qR$^?en>7}B<+bLr z=P8Zl+g6z8BoAK+*&!S*Lxg4H=iHeM1{Z#OnQzK`6ZfM@bHWi-#H`yuH;gH`n)8In zWUo{%!OIeG6-cZp`Bd*u95S@)br=;`zc(iMdy?zw<2*PBe2XzmxU=6QJBoGMKGFNL zUV!eT7=u4?JwQKa%{NwcRxZ9Wvyf#+>ZLK+cphzQLOVKBikBBxQHOnj6o#(Q$=)*C zOMw-dMms_eoQV#>AClXvJh_#NoB8mY1uKH55~}4ZydUM{P2`1{*ej}n1FfpxwgQ-= zkKYmdV1gv)*Agkklg*lJLuAM2>|;4M2w2@}2H!vQBv(dEyYP2;y>PNeq2wOvdLgvz zq_t@sRIf!+n*y@hT&Z~m4uoJmpaRe!EDv0P4M^$(MKF0qoSh~jQ~Q$t68#%lUeT31 zzg*gp*aM7E6*_t?l628rN~Pb%;wND)i~qz6JE{l@TBQ52o+(yyoHx*$C!-wKS2}~z zb+E5jA_yK2rdx1Bpa$V~G|h`@`#K%r2=AoN_nB2%4WwCIubV!{G)T5kz%cy~rX5eh+!1t{8qyq&UkJi&rz({Ddh+ldC(IF0Y`W?+b>0{Yr)S)~)_%Q7orYe2$b=oYL;DgS6XKS#u)$KBK-EJ$yna zwlvY;3tmB|vb|{8bY5DW2PhqktR#%0WECq6MVXJq6qRhiY}sE+5l%nY+BNCzaH}$C zG?L;QsY4{EEq75|opJm+XEb9oyiCycJtAROBu(MF-yc_F#9w|~u53mO_}gM<2`TvV z`W{X1rN1cE_PFhj;r+Q7awh7tAo+1{Ms1 z>$Urn8W_+mBHVmal9$aNpg{FNd?roHkuTmnCCQ9KdqVLwRYX`>v*O6=fW z+q`%;?kSuY{;jT?BwEcKpUB4A9F85Jz6HqB4$sgAOO0ZpNAAlOHv8jDESlaHPKu_Y zx*Q)#73bL(ick`E)B)l{?Tro1RW8Tif@8hg?ca~U0`X16RfqxI=t-Gy&dScQkK;?6 zUtY4}G!FCM;Btjh&GeL-@ylI~wQPEUBmHH~0jryMJe+_v&^qJB_jjOxENY!kpUb=v zbUvOzU6ctG`PdVkR9L$hqd|cvV?CQIaBwE)JSSONDQ z$M@)UdEVE^5%wwf>vtZc1>Pj@NKRGjP>h4OyrgZ7upkCUt}zlO~vgjU~j z{}^R4Q73YpP4XZBZL;|t$IZu+g=;Zl2&#_w_~;w4eHN8xmk)+j5|+3;8^H`F+C$2^}1qfybKAy!CPa?4SeG{u^2@( z(y`B#on2*-UNucnk~DhA{hhE#PPC?MgPExTEg439a&kZ^;@utKs+cZ9>wzb4qbgI3 zVJ`t^U@XGBrTVrV{y_w1`C3}5=1EufL8ZZqXlB=!%$6CUi3VjGZJx&aOYbC8wmJ{? zssm^d3Eh5ajGN5D!)!eUgkU~Y1FziV;p(NZs+GA^g~U-2lDl6|rWM#$6rQV^8g-o0 znN~?A=!GIL*;qENy~K|vvgqyVi6SLST^Vt838MTb-}FB)YKit1@?5MFu%@4X($Q}< zPC41QAcQm9Fz=1{vJc6_gX)K?ls~#V0Njl5qxM+_L#ZlXS4MMg5pd}fg^nlL{*#DM zr_EmXRV>i6+(Al>!o%PksYc_}z8|4Es zXV)-5X>xShfannZ{X;^<|FdtRrJe0pS@GF6G5H64@5S50s2noZmnV+ESQ& z-Ki_IPHb=Jf2J%9US>&kTc=@sK87%4^!soBKwgke=GK1@G#A(r3q9r^2#u8IInF&c zX8R9%26N@{A+()}ubLO^35(|vhNeY})sRy8z_K^Y4Ed{MGPqYHsfZigA`zZ>3@Kb( zX|G5+FsN<~3H2XZs6?Y$?{J_e_G=E?zybN zA7Jj@`M*&z$o(6oJ49O^{%^#PLPZi7RKe|kK|tQSWJ#bc%mB$9j)w(p(F9l^bb9!( z=BNIk|Mc!eU`@)hDE|?rD@Y(v1sX_>It{o#1j%vmZry)|>!`TS@(|1)lZ5$>Ql{;S4?FUbF%I&}X>)rqJ(A-kKd%`$)DdkQM;x!?it%7( z*BTY7oO^QX>oH>TK2Id5mP96Hz<>&696k$lW0RBOFE1yLK1)+W4T$7pNEl}Vd>9KK=Q_2)JU7gZ<+oI~J zd=AP`>!HSRFB0I$YGm}J=X2Bh&JIc2wAOtSe<>R)Y(HyiU)zn4t7o4M5T}+M$Ld8q zc=$OuRpo;#luwN2Jg4-4lEn-x%H0{>te89aBJ8O`fcjBv#7HT@@kIc`V?w>@IGT8S z;=sP1av!(IYsgI|ql{Rh=o1Xf6I)7?^f;Nv6!b(-2&?~kJ9ewYGT(wiqHKz}p(%rj+-=W78t!nV4=S9?t2j^G#DcV0$ zuHy*2z)j8Jf=gc6usr@LCaIA+d!Dgi`(39HtR)pGo!N!|%-uT?hwhjG)DWIZ{CYEK;0*mA zNe5g2M1uU^Qv%T8XMh~?-PnVYC;=1qLkzm71gH_;PcaRZzoP#j|4=n$zyRf*0sWx{ zP(!6wEK$GYH!GmBLV0CXzhh~%l*~LR0mW*PvxP!dH~IzfZ%D4L-8~LT2Qtk6wto&sG|v}0MDVhnt&&$UFn|23YE|T^g-{H@71Uw)5_G)VJ(0c zNJ`TN^fB(9k1)A!9H_ZAKnAi=|7$x(o$~(;@Iy$U)*mN#ZS{vu41J;l&;s62O`W^A z;JSYuTegXaYr09z7rsH0Jh) z1|fgR4870;ctLo6e}y#l0UZ!U*x${dKJXm0pZ0enZ2)M40`mXrwdGSoCk*cNMk@YP z8OmjNC%V^kUsE1v<^86=`EUJkTWJ2I2W2w{@Bl98OCtab;6M+I03XoI@n3}uV?Yzs zbaHR|?;${LPyQAKs%~=0.4.8"` +`pip install "scrapling[all]>=0.4.9"` Then do this to download all the browsers' dependencies: diff --git a/agent-skill/Scrapling-Skill/examples/README.md b/agent-skill/Scrapling-Skill/examples/README.md index d0f9a2b..85de486 100644 --- a/agent-skill/Scrapling-Skill/examples/README.md +++ b/agent-skill/Scrapling-Skill/examples/README.md @@ -9,7 +9,7 @@ All examples collect **all 100 quotes across 10 pages**. Make sure Scrapling is installed: ```bash -pip install "scrapling[all]>=0.4.8" +pip install "scrapling[all]>=0.4.9" scrapling install --force ``` diff --git a/pyproject.toml b/pyproject.toml index 8cb4768..9c390c0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta" [project] name = "scrapling" # Static version instead of a dynamic version so we can get better layer caching while building docker, check the docker file to understand -version = "0.4.8" +version = "0.4.9" description = "Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!" readme = {file = "README.md", content-type = "text/markdown"} license = {file = "LICENSE"} @@ -61,7 +61,7 @@ classifiers = [ "Typing :: Typed", ] dependencies = [ - "lxml>=6.1.0", + "lxml>=6.1.1", "cssselect>=1.4.0", "orjson>=3.11.8", "tld>=0.13.2", @@ -73,8 +73,8 @@ dependencies = [ fetchers = [ "click>=8.3.0", "curl_cffi>=0.15.0", - "playwright==1.59.0", - "patchright==1.59.1", + "playwright==1.60.0", + "patchright==1.60.1", "browserforge>=1.2.4", "apify-fingerprint-datapoints>=0.13.0", "msgspec>=0.21.1", diff --git a/scrapling/__init__.py b/scrapling/__init__.py index 3420e25..a5ff5eb 100644 --- a/scrapling/__init__.py +++ b/scrapling/__init__.py @@ -1,5 +1,5 @@ __author__ = "Karim Shoair (karim.shoair@pm.me)" -__version__ = "0.4.8" +__version__ = "0.4.9" __copyright__ = "Copyright (c) 2024 Karim Shoair" from typing import Any, TYPE_CHECKING diff --git a/scrapling/engines/toolbelt/fingerprints.py b/scrapling/engines/toolbelt/fingerprints.py index f4fdfc1..0c02002 100644 --- a/scrapling/engines/toolbelt/fingerprints.py +++ b/scrapling/engines/toolbelt/fingerprints.py @@ -13,8 +13,8 @@ from scrapling.core._types import Dict, Literal, Tuple __OS_NAME__ = platform_system() OSName = Literal["linux", "macos", "windows"] # Current versions hardcoded for now (Playwright doesn't allow to know the version of a browser without launching it) -chromium_version = 147 -chrome_version = 147 +chromium_version = 148 +chrome_version = 148 @lru_cache(1, typed=True) diff --git a/server.json b/server.json index e4e813e..deccdda 100644 --- a/server.json +++ b/server.json @@ -14,12 +14,12 @@ "mimeType": "image/png" } ], - "version": "0.4.8", + "version": "0.4.9", "packages": [ { "registryType": "pypi", "identifier": "scrapling", - "version": "0.4.8", + "version": "0.4.9", "runtimeHint": "uvx", "packageArguments": [ { diff --git a/setup.cfg b/setup.cfg index 1c967c8..4e3d8b6 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1,6 +1,6 @@ [metadata] name = scrapling -version = 0.4.8 +version = 0.4.9 author = Karim Shoair author_email = karim.shoair@pm.me description = Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be! diff --git a/tests/requirements.txt b/tests/requirements.txt index 83aa3dc..7c9c3ff 100644 --- a/tests/requirements.txt +++ b/tests/requirements.txt @@ -1,6 +1,6 @@ pytest>=2.8.0,<9 pytest-cov -playwright==1.59.0 +playwright==1.60.0 werkzeug<3.0.0 pytest-httpbin==2.1.0 pytest-asyncio diff --git a/tox.ini b/tox.ini index e740705..799ceae 100644 --- a/tox.ini +++ b/tox.ini @@ -10,8 +10,8 @@ envlist = pre-commit,py{310,311,312,313} usedevelop = True changedir = tests deps = - playwright==1.59.0 - patchright==1.59.1 + playwright==1.60.0 + patchright==1.60.1 -r{toxinidir}/tests/requirements.txt extras = ai,shell commands = From b3408c6f3c70eb8672c4178a55918ec567e2dad1 Mon Sep 17 00:00:00 2001 From: Karim shoair Date: Sun, 7 Jun 2026 16:44:18 +0300 Subject: [PATCH 09/11] docs: warn that the default installation doesn't include fetchers The quickstart examples import from `scrapling.fetchers`, which raises `ModuleNotFoundError` on a bare install since those dependencies live in the fetchers extra. Make the consequence explicit in the installation section across the docs and all README translations. Closes #343 --- README.md | 3 ++- docs/README_AR.md | 3 ++- docs/README_CN.md | 3 ++- docs/README_DE.md | 3 ++- docs/README_ES.md | 3 ++- docs/README_FR.md | 3 ++- docs/README_JP.md | 3 ++- docs/README_KR.md | 3 ++- docs/README_PT_BR.md | 3 ++- docs/README_RU.md | 3 ++- docs/index.md | 4 +++- 11 files changed, 23 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 4507844..e888c46 100644 --- a/README.md +++ b/README.md @@ -471,7 +471,8 @@ Scrapling requires Python 3.10 or higher: pip install scrapling ``` -This installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies. +> [!IMPORTANT] +> This installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies. So importing anything from `scrapling.fetchers` or `scrapling.spiders`, like in the examples above, will raise `ModuleNotFoundError` with this installation alone. If you are going to use any of the fetchers or spiders, install the fetchers' dependencies first as shown below. ### Optional Dependencies diff --git a/docs/README_AR.md b/docs/README_AR.md index 2070bc9..fdc5990 100644 --- a/docs/README_AR.md +++ b/docs/README_AR.md @@ -467,7 +467,8 @@ Scrapling ليس قوياً فحسب - بل هو أيضاً سريع بشكل م pip install scrapling ``` -يتضمن هذا التثبيت فقط محرك المحلل وتبعياته، بدون أي جوالب أو تبعيات سطر الأوامر. +> [!IMPORTANT] +> يتضمن هذا التثبيت فقط محرك المحلل وتبعياته، بدون أي جوالب أو تبعيات سطر الأوامر. لذلك، فإن استيراد أي شيء من `scrapling.fetchers` أو `scrapling.spiders`، كما في الأمثلة أعلاه، سيؤدي إلى خطأ `ModuleNotFoundError` مع هذا التثبيت وحده. إذا كنت ستستخدم أيًا من الجوالب أو العناكب، فقم أولًا بتثبيت تبعيات الجوالب كما هو موضح أدناه. ### التبعيات الاختيارية diff --git a/docs/README_CN.md b/docs/README_CN.md index 0750bcc..02c7415 100644 --- a/docs/README_CN.md +++ b/docs/README_CN.md @@ -467,7 +467,8 @@ Scrapling 需要 Python 3.10 或更高版本： pip install scrapling ``` -此安装仅包括解析器引擎及其依赖项，没有任何 Fetcher 或命令行依赖项。 +> [!IMPORTANT] +> 此安装仅包括解析器引擎及其依赖项，没有任何 Fetcher 或命令行依赖项。 因此，仅使用此安装时，像上面的示例那样从 `scrapling.fetchers` 或 `scrapling.spiders` 导入任何内容都会引发 `ModuleNotFoundError`。如果要使用任何 Fetcher 或 Spider，请先按照下面的说明安装 Fetcher 的依赖项。 ### 可选依赖项 diff --git a/docs/README_DE.md b/docs/README_DE.md index ac6e533..e4e320b 100644 --- a/docs/README_DE.md +++ b/docs/README_DE.md @@ -467,7 +467,8 @@ Scrapling erfordert Python 3.10 oder höher: pip install scrapling ``` -Diese Installation enthält nur die Parser-Engine und ihre Abhängigkeiten, ohne Fetcher oder Kommandozeilenabhängigkeiten. +> [!IMPORTANT] +> Diese Installation enthält nur die Parser-Engine und ihre Abhängigkeiten, ohne Fetcher oder Kommandozeilenabhängigkeiten. Daher führt der Import von allem aus `scrapling.fetchers` oder `scrapling.spiders`, wie in den Beispielen oben, mit dieser Installation allein zu einem `ModuleNotFoundError`. Wenn Sie einen der Fetcher oder Spider verwenden möchten, installieren Sie zuerst die Fetcher-Abhängigkeiten wie unten gezeigt. ### Optionale Abhängigkeiten diff --git a/docs/README_ES.md b/docs/README_ES.md index 1af1f9a..2105dd8 100644 --- a/docs/README_ES.md +++ b/docs/README_ES.md @@ -467,7 +467,8 @@ Scrapling requiere Python 3.10 o superior: pip install scrapling ``` -Esta instalación solo incluye el motor de análisis y sus dependencias, sin ningún fetcher ni dependencias de línea de comandos. +> [!IMPORTANT] +> Esta instalación solo incluye el motor de análisis y sus dependencias, sin ningún fetcher ni dependencias de línea de comandos. Por lo tanto, importar cualquier cosa desde `scrapling.fetchers` o `scrapling.spiders`, como en los ejemplos anteriores, lanzará un `ModuleNotFoundError` solo con esta instalación. Si va a usar alguno de los fetchers o spiders, instale primero las dependencias de los fetchers como se muestra a continuación. ### Dependencias Opcionales diff --git a/docs/README_FR.md b/docs/README_FR.md index c6d76ed..55a122c 100644 --- a/docs/README_FR.md +++ b/docs/README_FR.md @@ -467,7 +467,8 @@ Scrapling nécessite Python 3.10 ou supérieur : pip install scrapling ``` -Cette installation n'inclut que le moteur de parsing et ses dépendances, sans aucun fetcher ni dépendance en ligne de commande. +> [!IMPORTANT] +> Cette installation n'inclut que le moteur de parsing et ses dépendances, sans aucun fetcher ni dépendance en ligne de commande. Importer quoi que ce soit depuis `scrapling.fetchers` ou `scrapling.spiders`, comme dans les exemples ci-dessus, lèvera donc une `ModuleNotFoundError` avec cette seule installation. Si vous comptez utiliser l'un des fetchers ou spiders, installez d'abord les dépendances des fetchers comme indiqué ci-dessous. ### Dépendances optionnelles diff --git a/docs/README_JP.md b/docs/README_JP.md index dcf44fc..e57a0b5 100644 --- a/docs/README_JP.md +++ b/docs/README_JP.md @@ -467,7 +467,8 @@ Scrapling には Python 3.10 以上が必要です： pip install scrapling ``` -このインストールにはパーサーエンジンとその依存関係のみが含まれており、Fetcher やコマンドライン依存関係は含まれていません。 +> [!IMPORTANT] +> このインストールにはパーサーエンジンとその依存関係のみが含まれており、Fetcher やコマンドライン依存関係は含まれていません。 そのため、このインストールのみでは、上記の例のように `scrapling.fetchers` や `scrapling.spiders` から何かをインポートすると `ModuleNotFoundError` が発生します。Fetcher や Spider を使用する場合は、以下のように、まず Fetcher の依存関係をインストールしてください。 ### オプションの依存関係 diff --git a/docs/README_KR.md b/docs/README_KR.md index 18d2e05..f5c913b 100644 --- a/docs/README_KR.md +++ b/docs/README_KR.md @@ -467,7 +467,8 @@ Scrapling은 Python 3.10 이상이 필요합니다: pip install scrapling ``` -이 설치에는 파서 엔진과 의존성만 포함되며, Fetcher나 커맨드라인 의존성은 포함되지 않습니다. +> [!IMPORTANT] +> 이 설치에는 파서 엔진과 의존성만 포함되며, Fetcher나 커맨드라인 의존성은 포함되지 않습니다. 따라서 이 설치만으로는 위 예제처럼 `scrapling.fetchers`나 `scrapling.spiders`에서 무언가를 임포트하면 `ModuleNotFoundError`가 발생합니다. Fetcher나 Spider를 사용하려면 아래와 같이 먼저 Fetcher 의존성을 설치하세요. ### 선택적 의존성 diff --git a/docs/README_PT_BR.md b/docs/README_PT_BR.md index 4c7f617..3884614 100644 --- a/docs/README_PT_BR.md +++ b/docs/README_PT_BR.md @@ -469,7 +469,8 @@ O Scrapling requer Python 3.10 ou superior: pip install scrapling ``` -Esta instalação inclui apenas o motor de parsing e suas dependências, sem fetchers nem dependências de linha de comando. +> [!IMPORTANT] +> Esta instalação inclui apenas o motor de parsing e suas dependências, sem fetchers nem dependências de linha de comando. Portanto, importar qualquer coisa de `scrapling.fetchers` ou `scrapling.spiders`, como nos exemplos acima, lançará um `ModuleNotFoundError` apenas com esta instalação. Se você for usar algum dos fetchers ou spiders, instale primeiro as dependências dos fetchers como mostrado abaixo. ### Dependências Opcionais diff --git a/docs/README_RU.md b/docs/README_RU.md index 4dde2b9..ba5bb31 100644 --- a/docs/README_RU.md +++ b/docs/README_RU.md @@ -470,7 +470,8 @@ Scrapling требует Python 3.10 или выше: pip install scrapling ``` -Эта установка включает только движок парсера и его зависимости, без каких-либо Fetcher'ов или зависимостей командной строки. +> [!IMPORTANT] +> Эта установка включает только движок парсера и его зависимости, без каких-либо Fetcher'ов или зависимостей командной строки. Поэтому импорт чего-либо из `scrapling.fetchers` или `scrapling.spiders`, как в примерах выше, вызовет `ModuleNotFoundError` при такой установке. Если вы собираетесь использовать какие-либо Fetcher'ы или Spider'ы, сначала установите зависимости Fetcher'ов, как показано ниже. ### Опциональные зависимости diff --git a/docs/index.md b/docs/index.md index fdae518..b5a8ba4 100644 --- a/docs/index.md +++ b/docs/index.md @@ -180,7 +180,9 @@ Scrapling requires Python 3.10 or higher: pip install scrapling ``` -This installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies. +!!! warning + + This installation only includes the parser engine and its dependencies, without any fetchers or commandline dependencies. So importing anything from `scrapling.fetchers` or `scrapling.spiders`, like in the examples above, will raise `ModuleNotFoundError` with this installation alone. If you are going to use any of the fetchers or spiders, install the fetchers' dependencies first as shown below. ### Optional Dependencies From 5fdb46fea0c855f8306e56b8e92b48ccd31066c8 Mon Sep 17 00:00:00 2001 From: Karim shoair Date: Sun, 7 Jun 2026 18:11:38 +0300 Subject: [PATCH 10/11] docs: updating zensical to the latest version --- README.md | 2 +- docs/requirements.txt | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index e888c46..afdea47 100644 --- a/README.md +++ b/README.md @@ -209,7 +209,7 @@ MySpider().start() -Do you want to show your ad here? Click [here](https://github.com/sponsors/D4Vinci) and choose the tier that suites you! +Do you want to show your ad here? Click [here](https://github.com/sponsors/D4Vinci) and choose the tier that suits you! --- diff --git a/docs/requirements.txt b/docs/requirements.txt index fe3cea2..bf4b591 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,6 +1,6 @@ -zensical>=0.0.41 +zensical>=0.0.44 mkdocstrings>=1.0.4 -mkdocstrings-python>=2.0.3 +mkdocstrings-python>=2.0.4 griffe-inherited-docstrings>=1.1.3 griffe-runtime-objects>=0.3.1 griffe-sphinx>=0.2.1 From 74c5848060cae99e7076add01397609d5232e043 Mon Sep 17 00:00:00 2001 From: Karim shoair Date: Sun, 7 Jun 2026 18:35:18 +0300 Subject: [PATCH 11/11] fix: apply the session-level proxy when no per-request proxy is given The per-request proxy resolution never fell back to the session default, so FetcherSession(proxy=...) was silently ignored, and requests went direct. Same fix in the sync and async paths, with regression tests asserting on the proxy that reaches curl_cffi. Closes #295 --- scrapling/engines/static.py | 7 ++- tests/fetchers/async/test_requests_session.py | 51 ++++++++++++++++++- tests/fetchers/sync/test_requests_session.py | 51 ++++++++++++++++--- 3 files changed, 99 insertions(+), 10 deletions(-) diff --git a/scrapling/engines/static.py b/scrapling/engines/static.py index 9b3e951..6f18b2a 100644 --- a/scrapling/engines/static.py +++ b/scrapling/engines/static.py @@ -19,6 +19,7 @@ from scrapling.core._types import ( Unpack, Optional, Awaitable, + ProxyType, SUPPORTED_HTTP_METHODS, FollowRedirects, ) @@ -244,10 +245,11 @@ class _SyncSessionLogic(_ConfigurationLogic): try: for attempt in range(max_retries): + proxy: Optional[ProxyType] if self._proxy_rotator and static_proxy is None: proxy = self._proxy_rotator.get_proxy() else: - proxy = static_proxy + proxy = static_proxy or self._default_proxy request_args = self._merge_request_args(stealth=stealth, proxy=proxy, **kwargs) try: @@ -461,10 +463,11 @@ class _ASyncSessionLogic(_ConfigurationLogic): try: # Determine if we should use proxy rotation for attempt in range(max_retries): + proxy: Optional[ProxyType] if self._proxy_rotator and static_proxy is None: proxy = self._proxy_rotator.get_proxy() else: - proxy = static_proxy + proxy = static_proxy or self._default_proxy request_args = self._merge_request_args(stealth=stealth, proxy=proxy, **kwargs) try: diff --git a/tests/fetchers/async/test_requests_session.py b/tests/fetchers/async/test_requests_session.py index 3846e69..442a11f 100644 --- a/tests/fetchers/async/test_requests_session.py +++ b/tests/fetchers/async/test_requests_session.py @@ -1,6 +1,9 @@ +import pytest +from unittest.mock import patch, MagicMock, AsyncMock +from curl_cffi.curl import CurlError - -from scrapling.engines.static import AsyncFetcherClient +from scrapling.engines.static import _ASyncSessionLogic as AsyncFetcherSession, AsyncFetcherClient +from scrapling.engines.toolbelt import ProxyRotator class TestFetcherSession: @@ -13,3 +16,47 @@ class TestFetcherSession: # Should not have context manager methods assert client.__aenter__ is None assert client.__aexit__ is None + + @pytest.mark.asyncio + async def test_session_level_proxy_is_applied(self): + """Session-level proxy must reach the request, not be silently dropped (#295)""" + proxy = "http://10.255.255.1:9999" + + async with AsyncFetcherSession(proxy=proxy) as session: + with ( + patch.object(session._async_curl_session, "request", new=AsyncMock()) as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + await session.get("http://example.com") + + assert mocked_request.call_args.kwargs["proxy"] == proxy + + @pytest.mark.asyncio + async def test_per_request_proxy_overrides_session_proxy(self): + """A per-request proxy must take precedence over the session-level proxy""" + request_proxy = "http://10.255.255.2:9999" + + async with AsyncFetcherSession(proxy="http://10.255.255.1:9999") as session: + with ( + patch.object(session._async_curl_session, "request", new=AsyncMock()) as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + await session.get("http://example.com", proxy=request_proxy) + + assert mocked_request.call_args.kwargs["proxy"] == request_proxy + + @pytest.mark.asyncio + async def test_proxy_rotates_per_retry_attempt(self): + """With a rotator, every retry attempt must pull a fresh proxy""" + rotator = ProxyRotator(["http://p1:8080", "http://p2:8080"]) + + async with AsyncFetcherSession(proxy_rotator=rotator, retries=2, retry_delay=0) as session: + with ( + patch.object(session._async_curl_session, "request", new=AsyncMock()) as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + mocked_request.side_effect = [CurlError("transient"), MagicMock()] + await session.get("http://example.com") + + proxies_used = [call.kwargs["proxy"] for call in mocked_request.call_args_list] + assert proxies_used == ["http://p1:8080", "http://p2:8080"] diff --git a/tests/fetchers/sync/test_requests_session.py b/tests/fetchers/sync/test_requests_session.py index 152fbc4..2620e37 100644 --- a/tests/fetchers/sync/test_requests_session.py +++ b/tests/fetchers/sync/test_requests_session.py @@ -1,7 +1,9 @@ import pytest - +from unittest.mock import patch, MagicMock +from curl_cffi.curl import CurlError from scrapling.engines.static import _SyncSessionLogic as FetcherSession, FetcherClient +from scrapling.engines.toolbelt import ProxyRotator class TestFetcherSession: @@ -9,11 +11,7 @@ class TestFetcherSession: def test_fetcher_session_creation(self): """Test FetcherSession creation""" - session = FetcherSession( - timeout=30, - retries=3, - stealthy_headers=True - ) + session = FetcherSession(timeout=30, retries=3, stealthy_headers=True) assert session._default_timeout == 30 assert session._default_retries == 3 @@ -43,3 +41,44 @@ class TestFetcherSession: # Should not have context manager methods assert client.__enter__ is None assert client.__exit__ is None + + def test_session_level_proxy_is_applied(self): + """Session-level proxy must reach the request, not be silently dropped (#295)""" + proxy = "http://10.255.255.1:9999" + + with FetcherSession(proxy=proxy) as session: + with ( + patch.object(session._curl_session, "request") as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + session.get("http://example.com") + + assert mocked_request.call_args.kwargs["proxy"] == proxy + + def test_per_request_proxy_overrides_session_proxy(self): + """A per-request proxy must take precedence over the session-level proxy""" + request_proxy = "http://10.255.255.2:9999" + + with FetcherSession(proxy="http://10.255.255.1:9999") as session: + with ( + patch.object(session._curl_session, "request") as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + session.get("http://example.com", proxy=request_proxy) + + assert mocked_request.call_args.kwargs["proxy"] == request_proxy + + def test_proxy_rotates_per_retry_attempt(self): + """With a rotator, every retry attempt must pull a fresh proxy""" + rotator = ProxyRotator(["http://p1:8080", "http://p2:8080"]) + + with FetcherSession(proxy_rotator=rotator, retries=2, retry_delay=0) as session: + with ( + patch.object(session._curl_session, "request") as mocked_request, + patch("scrapling.engines.static.ResponseFactory.from_http_request", return_value=MagicMock()), + ): + mocked_request.side_effect = [CurlError("transient"), MagicMock()] + session.get("http://example.com") + + proxies_used = [call.kwargs["proxy"] for call in mocked_request.call_args_list] + assert proxies_used == ["http://p1:8080", "http://p2:8080"]