Skip to content

Commit 53fc747

Browse files
YahiaBakourYahiaBakour
authored
Merge pull request #38 from context-dot-dev/release-please--branches--main--changes--next
release: 0.32.0
2 parents cc26a5a + 45bbf2b commit 53fc747

10 files changed

Lines changed: 147 additions & 5 deletions

File tree

‎.release-please-manifest.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
{
2-
".": "0.31.0"
2+
".": "0.32.0"
33
}

‎.stats.yml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
configured_endpoints: 25
2-
openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev/context.dev-de0ba2ed18ec7265b0b20d9639b3da207dd33e354f0a856091902291c6661830.yml
3-
openapi_spec_hash: ae25efc2ac6bcab54bc3f4efaab73a55
2+
openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/context-dev/context.dev-8f6bc62256b5a4aa44e82389bfefee1d73172856c407567bba11a82fd4203641.yml
3+
openapi_spec_hash: 8b7230de56ecbec4712fa1e81067a75c
44
config_hash: f86a4e06ae5ed725aa79d58d7a8dc27c

‎CHANGELOG.md‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,13 @@
11
# Changelog
22

3+
## 0.32.0 (2026-06-07)
4+
5+
Full Changelog: [v0.31.0...v0.32.0](https://github.com/context-dot-dev/context-python-sdk/compare/v0.31.0...v0.32.0)
6+
7+
### Features
8+
9+
* **api:** api update ([7ef921a](https://github.com/context-dot-dev/context-python-sdk/commit/7ef921a84ef020f5c31458d3975be33e5befd065))
10+
311
## 0.31.0 (2026-06-07)
412

513
Full Changelog: [v0.30.0...v0.31.0](https://github.com/context-dot-dev/context-python-sdk/compare/v0.30.0...v0.31.0)

‎pyproject.toml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
[project]
22
name = "context.dev"
3-
version = "0.31.0"
3+
version = "0.32.0"
44
description = "The official Python library for the context.dev API"
55
dynamic = ["readme"]
66
license = "Apache-2.0"

‎src/context/dev/_version.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
22

33
__title__ = "context.dev"
4-
__version__ = "0.31.0" # x-release-please-version
4+
__version__ = "0.32.0" # x-release-please-version

‎src/context/dev/resources/web.py‎

Lines changed: 74 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -503,10 +503,12 @@ def web_crawl_md(
503503
self,
504504
*,
505505
url: str,
506+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
506507
follow_subdomains: bool | Omit = omit,
507508
include_frames: bool | Omit = omit,
508509
include_images: bool | Omit = omit,
509510
include_links: bool | Omit = omit,
511+
include_selectors: SequenceNotStr[str] | Omit = omit,
510512
max_age_ms: int | Omit = omit,
511513
max_depth: int | Omit = omit,
512514
max_pages: int | Omit = omit,
@@ -531,6 +533,10 @@ def web_crawl_md(
531533
Args:
532534
url: The starting URL for the crawl (must include http:// or https:// protocol)
533535
536+
exclude_selectors: CSS selectors to remove before each crawled page is converted to Markdown.
537+
Applied after includeSelectors. Exclusion takes precedence: an element matching
538+
both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
539+
534540
follow_subdomains: When true, follow links on subdomains of the starting URL's domain (e.g.
535541
docs.example.com when starting from example.com). www and apex are always
536542
treated as equivalent.
@@ -542,6 +548,11 @@ def web_crawl_md(
542548
543549
include_links: Preserve hyperlinks in the Markdown output
544550
551+
include_selectors: CSS selectors. When provided, only matching HTML subtrees (and their
552+
descendants) are kept before each crawled page is converted to Markdown. When
553+
omitted, the entire document is kept. Examples: "article.main", "#content",
554+
"[role=main]".
555+
545556
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
546557
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
547558
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -585,10 +596,12 @@ def web_crawl_md(
585596
body=maybe_transform(
586597
{
587598
"url": url,
599+
"exclude_selectors": exclude_selectors,
588600
"follow_subdomains": follow_subdomains,
589601
"include_frames": include_frames,
590602
"include_images": include_images,
591603
"include_links": include_links,
604+
"include_selectors": include_selectors,
592605
"max_age_ms": max_age_ms,
593606
"max_depth": max_depth,
594607
"max_pages": max_pages,
@@ -612,8 +625,10 @@ def web_scrape_html(
612625
self,
613626
*,
614627
url: str,
628+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
615629
headers: Dict[str, str] | Omit = omit,
616630
include_frames: bool | Omit = omit,
631+
include_selectors: SequenceNotStr[str] | Omit = omit,
617632
max_age_ms: int | Omit = omit,
618633
pdf: web_web_scrape_html_params.Pdf | Omit = omit,
619634
timeout_ms: int | Omit = omit,
@@ -631,12 +646,20 @@ def web_scrape_html(
631646
Args:
632647
url: Full URL to scrape (must include http:// or https:// protocol)
633648
649+
exclude_selectors: CSS selectors to remove from the result. Applied after includeSelectors.
650+
Exclusion takes precedence: an element matching both is removed. Examples:
651+
"nav", "footer", ".ad-banner", "[aria-hidden=true]".
652+
634653
headers: Optional outbound HTTP headers forwarded only to the target URL, sent as
635654
deep-object query params such as headers[X-Custom]=value. When provided, caching
636655
is bypassed: the result is neither read from nor written to cache.
637656
638657
include_frames: When true, iframes are rendered inline into the returned HTML.
639658
659+
include_selectors: CSS selectors. When provided, only matching subtrees (and their descendants) are
660+
kept and everything else is dropped. When omitted, the entire document is kept.
661+
Examples: "article.main", "#content", "[role=main]".
662+
640663
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
641664
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
642665
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -670,8 +693,10 @@ def web_scrape_html(
670693
query=maybe_transform(
671694
{
672695
"url": url,
696+
"exclude_selectors": exclude_selectors,
673697
"headers": headers,
674698
"include_frames": include_frames,
699+
"include_selectors": include_selectors,
675700
"max_age_ms": max_age_ms,
676701
"pdf": pdf,
677702
"timeout_ms": timeout_ms,
@@ -759,10 +784,12 @@ def web_scrape_md(
759784
self,
760785
*,
761786
url: str,
787+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
762788
headers: Dict[str, str] | Omit = omit,
763789
include_frames: bool | Omit = omit,
764790
include_images: bool | Omit = omit,
765791
include_links: bool | Omit = omit,
792+
include_selectors: SequenceNotStr[str] | Omit = omit,
766793
max_age_ms: int | Omit = omit,
767794
pdf: web_web_scrape_md_params.Pdf | Omit = omit,
768795
shorten_base64_images: bool | Omit = omit,
@@ -783,6 +810,10 @@ def web_scrape_md(
783810
url: Full URL to scrape into LLM usable Markdown (must include http:// or https://
784811
protocol)
785812
813+
exclude_selectors: CSS selectors to remove before conversion to Markdown. Applied after
814+
includeSelectors. Exclusion takes precedence: an element matching both is
815+
removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
816+
786817
headers: Optional outbound HTTP headers forwarded only to the target URL, sent as
787818
deep-object query params such as headers[X-Custom]=value. When provided, caching
788819
is bypassed: the result is neither read from nor written to cache.
@@ -793,6 +824,10 @@ def web_scrape_md(
793824
794825
include_links: Preserve hyperlinks in Markdown output
795826
827+
include_selectors: CSS selectors. When provided, only matching HTML subtrees (and their
828+
descendants) are kept before conversion to Markdown. When omitted, the entire
829+
document is kept. Examples: "article.main", "#content", "[role=main]".
830+
796831
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
797832
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
798833
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -830,10 +865,12 @@ def web_scrape_md(
830865
query=maybe_transform(
831866
{
832867
"url": url,
868+
"exclude_selectors": exclude_selectors,
833869
"headers": headers,
834870
"include_frames": include_frames,
835871
"include_images": include_images,
836872
"include_links": include_links,
873+
"include_selectors": include_selectors,
837874
"max_age_ms": max_age_ms,
838875
"pdf": pdf,
839876
"shorten_base64_images": shorten_base64_images,
@@ -1369,10 +1406,12 @@ async def web_crawl_md(
13691406
self,
13701407
*,
13711408
url: str,
1409+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
13721410
follow_subdomains: bool | Omit = omit,
13731411
include_frames: bool | Omit = omit,
13741412
include_images: bool | Omit = omit,
13751413
include_links: bool | Omit = omit,
1414+
include_selectors: SequenceNotStr[str] | Omit = omit,
13761415
max_age_ms: int | Omit = omit,
13771416
max_depth: int | Omit = omit,
13781417
max_pages: int | Omit = omit,
@@ -1397,6 +1436,10 @@ async def web_crawl_md(
13971436
Args:
13981437
url: The starting URL for the crawl (must include http:// or https:// protocol)
13991438
1439+
exclude_selectors: CSS selectors to remove before each crawled page is converted to Markdown.
1440+
Applied after includeSelectors. Exclusion takes precedence: an element matching
1441+
both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
1442+
14001443
follow_subdomains: When true, follow links on subdomains of the starting URL's domain (e.g.
14011444
docs.example.com when starting from example.com). www and apex are always
14021445
treated as equivalent.
@@ -1408,6 +1451,11 @@ async def web_crawl_md(
14081451
14091452
include_links: Preserve hyperlinks in the Markdown output
14101453
1454+
include_selectors: CSS selectors. When provided, only matching HTML subtrees (and their
1455+
descendants) are kept before each crawled page is converted to Markdown. When
1456+
omitted, the entire document is kept. Examples: "article.main", "#content",
1457+
"[role=main]".
1458+
14111459
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
14121460
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
14131461
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -1451,10 +1499,12 @@ async def web_crawl_md(
14511499
body=await async_maybe_transform(
14521500
{
14531501
"url": url,
1502+
"exclude_selectors": exclude_selectors,
14541503
"follow_subdomains": follow_subdomains,
14551504
"include_frames": include_frames,
14561505
"include_images": include_images,
14571506
"include_links": include_links,
1507+
"include_selectors": include_selectors,
14581508
"max_age_ms": max_age_ms,
14591509
"max_depth": max_depth,
14601510
"max_pages": max_pages,
@@ -1478,8 +1528,10 @@ async def web_scrape_html(
14781528
self,
14791529
*,
14801530
url: str,
1531+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
14811532
headers: Dict[str, str] | Omit = omit,
14821533
include_frames: bool | Omit = omit,
1534+
include_selectors: SequenceNotStr[str] | Omit = omit,
14831535
max_age_ms: int | Omit = omit,
14841536
pdf: web_web_scrape_html_params.Pdf | Omit = omit,
14851537
timeout_ms: int | Omit = omit,
@@ -1497,12 +1549,20 @@ async def web_scrape_html(
14971549
Args:
14981550
url: Full URL to scrape (must include http:// or https:// protocol)
14991551
1552+
exclude_selectors: CSS selectors to remove from the result. Applied after includeSelectors.
1553+
Exclusion takes precedence: an element matching both is removed. Examples:
1554+
"nav", "footer", ".ad-banner", "[aria-hidden=true]".
1555+
15001556
headers: Optional outbound HTTP headers forwarded only to the target URL, sent as
15011557
deep-object query params such as headers[X-Custom]=value. When provided, caching
15021558
is bypassed: the result is neither read from nor written to cache.
15031559
15041560
include_frames: When true, iframes are rendered inline into the returned HTML.
15051561
1562+
include_selectors: CSS selectors. When provided, only matching subtrees (and their descendants) are
1563+
kept and everything else is dropped. When omitted, the entire document is kept.
1564+
Examples: "article.main", "#content", "[role=main]".
1565+
15061566
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
15071567
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
15081568
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -1536,8 +1596,10 @@ async def web_scrape_html(
15361596
query=await async_maybe_transform(
15371597
{
15381598
"url": url,
1599+
"exclude_selectors": exclude_selectors,
15391600
"headers": headers,
15401601
"include_frames": include_frames,
1602+
"include_selectors": include_selectors,
15411603
"max_age_ms": max_age_ms,
15421604
"pdf": pdf,
15431605
"timeout_ms": timeout_ms,
@@ -1625,10 +1687,12 @@ async def web_scrape_md(
16251687
self,
16261688
*,
16271689
url: str,
1690+
exclude_selectors: SequenceNotStr[str] | Omit = omit,
16281691
headers: Dict[str, str] | Omit = omit,
16291692
include_frames: bool | Omit = omit,
16301693
include_images: bool | Omit = omit,
16311694
include_links: bool | Omit = omit,
1695+
include_selectors: SequenceNotStr[str] | Omit = omit,
16321696
max_age_ms: int | Omit = omit,
16331697
pdf: web_web_scrape_md_params.Pdf | Omit = omit,
16341698
shorten_base64_images: bool | Omit = omit,
@@ -1649,6 +1713,10 @@ async def web_scrape_md(
16491713
url: Full URL to scrape into LLM usable Markdown (must include http:// or https://
16501714
protocol)
16511715
1716+
exclude_selectors: CSS selectors to remove before conversion to Markdown. Applied after
1717+
includeSelectors. Exclusion takes precedence: an element matching both is
1718+
removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
1719+
16521720
headers: Optional outbound HTTP headers forwarded only to the target URL, sent as
16531721
deep-object query params such as headers[X-Custom]=value. When provided, caching
16541722
is bypassed: the result is neither read from nor written to cache.
@@ -1659,6 +1727,10 @@ async def web_scrape_md(
16591727
16601728
include_links: Preserve hyperlinks in Markdown output
16611729
1730+
include_selectors: CSS selectors. When provided, only matching HTML subtrees (and their
1731+
descendants) are kept before conversion to Markdown. When omitted, the entire
1732+
document is kept. Examples: "article.main", "#content", "[role=main]".
1733+
16621734
max_age_ms: Return a cached result if a prior scrape for the same parameters exists and is
16631735
younger than this many milliseconds. Defaults to 1 day (86400000 ms) when
16641736
omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.
@@ -1696,10 +1768,12 @@ async def web_scrape_md(
16961768
query=await async_maybe_transform(
16971769
{
16981770
"url": url,
1771+
"exclude_selectors": exclude_selectors,
16991772
"headers": headers,
17001773
"include_frames": include_frames,
17011774
"include_images": include_images,
17021775
"include_links": include_links,
1776+
"include_selectors": include_selectors,
17031777
"max_age_ms": max_age_ms,
17041778
"pdf": pdf,
17051779
"shorten_base64_images": shorten_base64_images,

‎src/context/dev/types/web_web_crawl_md_params.py‎

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@
44

55
from typing_extensions import Required, Annotated, TypedDict
66

7+
from .._types import SequenceNotStr
78
from .._utils import PropertyInfo
89

910
__all__ = ["WebWebCrawlMdParams", "Pdf"]
@@ -13,6 +14,13 @@ class WebWebCrawlMdParams(TypedDict, total=False):
1314
url: Required[str]
1415
"""The starting URL for the crawl (must include http:// or https:// protocol)"""
1516

17+
exclude_selectors: Annotated[SequenceNotStr[str], PropertyInfo(alias="excludeSelectors")]
18+
"""CSS selectors to remove before each crawled page is converted to Markdown.
19+
20+
Applied after includeSelectors. Exclusion takes precedence: an element matching
21+
both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
22+
"""
23+
1624
follow_subdomains: Annotated[bool, PropertyInfo(alias="followSubdomains")]
1725
"""When true, follow links on subdomains of the starting URL's domain (e.g.
1826
@@ -32,6 +40,14 @@ class WebWebCrawlMdParams(TypedDict, total=False):
3240
include_links: Annotated[bool, PropertyInfo(alias="includeLinks")]
3341
"""Preserve hyperlinks in the Markdown output"""
3442

43+
include_selectors: Annotated[SequenceNotStr[str], PropertyInfo(alias="includeSelectors")]
44+
"""CSS selectors.
45+
46+
When provided, only matching HTML subtrees (and their descendants) are kept
47+
before each crawled page is converted to Markdown. When omitted, the entire
48+
document is kept. Examples: "article.main", "#content", "[role=main]".
49+
"""
50+
3551
max_age_ms: Annotated[int, PropertyInfo(alias="maxAgeMs")]
3652
"""
3753
Return a cached result if a prior scrape for the same parameters exists and is

‎src/context/dev/types/web_web_scrape_html_params.py‎

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@
55
from typing import Dict
66
from typing_extensions import Required, Annotated, TypedDict
77

8+
from .._types import SequenceNotStr
89
from .._utils import PropertyInfo
910

1011
__all__ = ["WebWebScrapeHTMLParams", "Pdf"]
@@ -14,6 +15,13 @@ class WebWebScrapeHTMLParams(TypedDict, total=False):
1415
url: Required[str]
1516
"""Full URL to scrape (must include http:// or https:// protocol)"""
1617

18+
exclude_selectors: Annotated[SequenceNotStr[str], PropertyInfo(alias="excludeSelectors")]
19+
"""CSS selectors to remove from the result.
20+
21+
Applied after includeSelectors. Exclusion takes precedence: an element matching
22+
both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".
23+
"""
24+
1725
headers: Dict[str, str]
1826
"""
1927
Optional outbound HTTP headers forwarded only to the target URL, sent as
@@ -24,6 +32,14 @@ class WebWebScrapeHTMLParams(TypedDict, total=False):
2432
include_frames: Annotated[bool, PropertyInfo(alias="includeFrames")]
2533
"""When true, iframes are rendered inline into the returned HTML."""
2634

35+
include_selectors: Annotated[SequenceNotStr[str], PropertyInfo(alias="includeSelectors")]
36+
"""CSS selectors.
37+
38+
When provided, only matching subtrees (and their descendants) are kept and
39+
everything else is dropped. When omitted, the entire document is kept. Examples:
40+
"article.main", "#content", "[role=main]".
41+
"""
42+
2743
max_age_ms: Annotated[int, PropertyInfo(alias="maxAgeMs")]
2844
"""
2945
Return a cached result if a prior scrape for the same parameters exists and is

0 commit comments

Comments
 (0)