scrapegraphai 2.1.7__tar.gz → 2.2.0__tar.gz

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/.github/workflows/test-suite.yml

@@ -38,6 +38,7 @@ jobs:
       - name: Run unit tests
         run: >
           uv run pytest
+          tests/test_atlascloud_model.py
           tests/test_batch_api.py
           tests/test_csv_scraper_multi_graph.py
           tests/test_depth_search_graph.py
@@ -46,4 +47,5 @@ jobs:
           tests/test_scrape_do.py
           tests/test_search_graph.py
           tests/utils/convert_to_md_test.py
+          tests/utils/output_parser_test.py
           tests/utils/parse_state_keys_test.py

scrapegraphai-2.2.0/AGENTS.md

@@ -0,0 +1,136 @@
+# AGENTS.md
+
+Instructions for AI coding agents (Claude Code, Codex, Cursor, Copilot agents, …)
+working on **ScrapeGraphAI**. Human contributors should read
+[CONTRIBUTING.md](CONTRIBUTING.md); everything here is in addition to it.
+
+---
+
+## 1. Golden rule: everything goes to `pre/beta`
+
+**`main` is never written to directly. All work is based on and merged into `pre/beta`.**
+
+`pre/beta` is the prerelease branch: pushes to it publish a `beta` prerelease via
+semantic-release (see `.releaserc.yml`). `main` only receives releases when a
+maintainer promotes `pre/beta`.
+
+```bash
+# 1. always start from an up-to-date pre/beta
+git fetch origin
+git checkout -b feat/my-change origin/pre/beta
+
+# 2. commit your work
+git add <only the files you touched>
+git commit -m "feat(nodes): add X"
+
+# 3. push and open the PR against pre/beta
+git push -u origin feat/my-change
+gh pr create --base pre/beta --title "feat(nodes): add X" --body "..."
+```
+
+Checklist before you commit:
+
+- [ ] The branch is based on `origin/pre/beta` (`git merge-base --is-ancestor origin/pre/beta HEAD`).
+- [ ] The PR base is `pre/beta`, **not** `main`.
+- [ ] No commits directly on `main` or `pre/beta`, no force-push to either.
+- [ ] One logical change per branch/PR.
+
+If a task genuinely requires targeting `main` (e.g. a hotfix on a released
+version), stop and ask a maintainer first.
+
+## 2. Environment setup
+
+Python `>=3.12`, dependencies managed with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv sync                     # create the venv and install deps
+uv run pre-commit install   # install the git hooks
+```
+
+Never hand-edit `uv.lock`; regenerate it with `uv lock` / `uv sync` and commit
+the result only when you actually changed dependencies in `pyproject.toml`.
+
+## 3. Checks to run before pushing
+
+```bash
+make lint         # ruff + black --check + isort --check-only
+make type-check   # mypy (strict)
+make test         # pytest with coverage
+make pre-commit   # run all hooks on all files
+```
+
+Run at least `make lint` and the tests covering what you touched. Report the
+real result: if something fails or you skipped a step, say so in the PR
+description instead of implying a clean run.
+
+Style: PEP 8 + Google Python docstrings, `black` formatting, line length 88.
+Match the conventions of the surrounding file rather than introducing new ones.
+
+## 4. Commit messages
+
+Commits are parsed by semantic-release (Conventional Commits, `conventionalcommits`
+preset), so the message decides the next version number. Use:
+
+```
+feat:     ✨ new feature          -> minor bump
+fix:      🐛 bug fix              -> patch bump
+docs:     📚 documentation
+style:    💅 formatting only
+refactor: ♻️  no behaviour change
+perf:     ⚡ performance
+test:     🧪 tests
+build:    📦 build system / deps
+ci:       🤖 CI configuration
+chore:    🧹 everything else
+```
+
+Format: `type(optional-scope): imperative summary`, optional body, and
+`BREAKING CHANGE:` in the footer for incompatible changes. Reference issues with
+`Fixes #123`.
+
+## 5. Files agents must not touch
+
+- `CHANGELOG.md` and the `version` field in `pyproject.toml` — owned by
+  semantic-release; editing them by hand breaks releases.
+- Git tags and release notes on GitHub.
+- `.github/workflows/*` — only when the task is explicitly about CI.
+- Anything under `htmlcov/`, `coverage.xml`, `.pytest_cache/`, `__pycache__/`:
+  build artifacts, never commit them.
+
+Also: never commit secrets. API keys go in a local `.env` (git-ignored) and are
+read via `os.getenv`; examples and tests must use placeholders such as
+`OPENAI_APIKEY` from the environment.
+
+## 6. Repository layout
+
+```
+scrapegraphai/
+├── graphs/        # pipelines (SmartScraperGraph, SearchGraph, …)
+├── nodes/         # single graph steps (FetchNode, ParseNode, GenerateAnswerNode, …)
+├── models/        # LLM wrappers and token/model metadata
+├── docloaders/    # loaders (ChromiumLoader, …)
+├── prompts/       # prompt templates
+├── helpers/       # shared constants and schemas
+├── integrations/  # third-party / managed-API integrations
+└── utils/         # utilities (html cleanup, tokenization, …)
+examples/          # runnable usage examples, one folder per graph
+tests/             # pytest suite, mirrors the package layout
+docs/              # documentation sources
+```
+
+When adding a node or graph, register it in the corresponding `__init__.py` and
+add a test under `tests/` next to the existing ones for that layer. New
+user-facing features need an entry in `examples/` and, when they change public
+behaviour, a docs update.
+
+## 7. Working style expected from agents
+
+- Prefer small, reviewable diffs; do not reformat or "clean up" untouched files.
+- Do not add dependencies unless the task requires it — say why in the PR.
+- Write all commits, PR titles/bodies, issue comments, code comments and
+  docstrings **in English**.
+- Do not delete or rewrite existing tests to make a change pass.
+- If a test is already failing on `pre/beta`, mention it rather than silently
+  fixing unrelated things in the same PR.
+- Never commit other people's in-progress work: check `git status` and stage
+  only the files belonging to your change.

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/CHANGELOG.md

@@ -1,3 +1,68 @@
+## [2.2.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.1.7...v2.2.0) (2026-08-19)
+
+
+### Features
+
+* add OpenAI Batch API support for SmartScraperMultiGraph ([#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036)) ([9d4eba1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/9d4eba1f154953e401982da7eff85686293b9a48))
+* upgrade MiniMax default model to M3 ([#1080](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1080)) ([1b16c26](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/1b16c268f4e9044c1386ccfaf67b38692b487e5a))
+
+
+### Bug Fixes
+
+* lazy imports to prevent torchcodec FFmpeg DLL crash on Windows ([#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089)) ([2f55377](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/2f55377010fb16c81655aa1c8d08b88daa880797))
+* **nodes:** tolerate doubled-brace JSON output from models like DeepSeek ([#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)) ([aaa5d2c](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/aaa5d2cf6d2657f8e8a3b9020ab8b40cdb311c46))
+* update broken test imports to match current API ([536e5ad](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/536e5adcde179a12ec146bd8a10cbf654e0eeeaa))
+* **batch:** use langchain_core.prompts for PromptTemplate import ([24127da](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/24127dad8c049601befd0e9157ec8a26609b45e1))
+
+
+### Docs
+
+* add AGENTS.md with contribution rules for AI agents ([3b2f986](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/3b2f986612bbc70879a0337197a1064cf5875245))
+
+
+### CI
+
+* **release:** 1.60.0-beta.2 [skip ci] ([54d1473](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/54d147309dc7a1ce1b191c3e4feb927ee3ff4392)), closes [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036)
+* **release:** 1.60.0-beta.3 [skip ci] ([637c696](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/637c696da77da1bb916a4ece03bd66fea50be47e))
+* **release:** 1.76.0-beta.1 [skip ci] ([35ec272](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/35ec272b6f267a164fac67a26787396db548e2a7)), closes [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036)
+* **release:** 2.1.0-beta.1 [skip ci] ([a2ea9eb](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/a2ea9eb45f1406aac054e057c19a6bbf806fc38a)), closes [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036)
+* **release:** 2.2.0-beta.1 [skip ci] ([e7a75dc](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/e7a75dcb465feaa4ff2f87cf63777658728ecf3f)), closes [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036) [#1036](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1036)
+* **release:** 2.2.0-beta.2 [skip ci] ([73d850c](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/73d850c60d63d31201678de2cc1da68a9216b976)), closes [#1080](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1080)
+* **release:** 2.2.0-beta.3 [skip ci] ([b528325](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/b528325f04ccaf84010decb32ca32efd6c281f90)), closes [#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076) [#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074) [#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076) [#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074)
+* **release:** 2.2.0-beta.4 [skip ci] ([861ab77](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/861ab770abbe03314561f91835b1ac40ad6499f8)), closes [#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)
+* **release:** 2.2.0-beta.5 [skip ci] ([87655f8](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/87655f8208cd4814c34d9ebba55932c20817d7a1)), closes [#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089)
+* **release:** 2.2.0-beta.6 [skip ci] ([cb8f9b5](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/cb8f9b58e0e9a7c27b2178a4818e6cdd5f9f07a1)), closes [#1121](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1121) [#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089) [#1092](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1092) [#1100](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1100) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1103](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1103) [#1091](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1091) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089) [#1092](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1092) [#1100](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1100) [#1091](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1091) [#1095](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1095) [#1103](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1103) [#1121](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1121) [#1095](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1095) [#1104](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1104) [#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)
+* run the two new deterministic unit suites ([23e3d06](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/23e3d064e3850de222bcfc13907695278ca3bba9)), closes [#1104](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1104) [#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)
+
+## [2.2.0-beta.6](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.5...v2.2.0-beta.6) (2026-08-19)
+
+
+### Bug Fixes
+
+* **graph:** expose when the 8192 token fallback was used ([470da9d](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/470da9d51d6220a8020ee8a1d91b618d3d622042)), closes [#1121](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1121)
+* lazy imports to prevent torchcodec FFmpeg DLL crash on Windows ([#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089)) ([#1092](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1092)) ([e5c2a42](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/e5c2a4292174bae948731379c88aafb14197ec6c))
+* pop model_tokens so it is not forwarded to the model client ([#1100](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1100)) ([d2b970c](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/d2b970ca77da64b6b6b91fa2353f2e41b9cfe105))
+* **search:** restore SearchGraph by migrating DuckDuckGo backend to ddgs ([#1083](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1083)) ([2139e37](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/2139e37c0addfb9039e3b985bb33801f20e4e05b)), closes [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082)
+* update MiniMax model metadata and endpoints ([#1103](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1103)) ([e5f8f2b](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/e5f8f2bf008cd7ce7f3d5980bf6f98e6153b2264))
+
+
+### Docs
+
+* add AGENTS.md with contribution rules for AI agents ([3b2f986](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/3b2f986612bbc70879a0337197a1064cf5875245))
+* **readme:** add Open Source vs Managed API comparison ([#1091](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1091)) ([ef3523b](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/ef3523b1e1c62052b5c0e6b14cebe7933441a7e5))
+* swap Integrations infographic for new API banner; fix CTA links ([71ab440](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/71ab4406867ef02c22349c2dedc18c57d8bdfdec))
+
+
+### CI
+
+* **release:** 2.1.3 [skip ci] ([cfb815f](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/cfb815fb0bba3dfc8262a24a7ddab28e22e13893)), closes [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082)
+* **release:** 2.1.4 [skip ci] ([7fc9c57](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/7fc9c57a0bb861d829f38ed672e35c5ba0e6c79c)), closes [#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089) [#1092](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1092)
+* **release:** 2.1.5 [skip ci] ([c9e0bd0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/c9e0bd036a1f5def8ac92759cda90ba52e3b35e5)), closes [#1100](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1100) [#1091](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1091) [#1095](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1095)
+* **release:** 2.1.6 [skip ci] ([27d9d28](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/27d9d289f964844a28006f6d7d1518e293fd49ff)), closes [#1103](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1103)
+* **release:** 2.1.7 [skip ci] ([ca112db](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/ca112db4d8b1bd34961e9f1b7e3adf0c7d600c01)), closes [#1121](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1121)
+* run only deterministic unit suites in Test Suite workflow ([#1095](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1095)) ([037a42e](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/037a42ed73354c8b3eabd9dcc28236152602ef9e))
+* run the two new deterministic unit suites ([23e3d06](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/23e3d064e3850de222bcfc13907695278ca3bba9)), closes [#1104](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1104) [#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)
+
 ## [2.1.7](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.1.6...v2.1.7) (2026-08-19)
 
 
@@ -68,6 +133,44 @@
 ## [2.2.0-beta.2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.1...v2.2.0-beta.2) (2026-06-01)
 
 
+### Features
+
+* upgrade MiniMax default model to M3 ([#1080](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1080)) ([1b16c26](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/1b16c268f4e9044c1386ccfaf67b38692b487e5a))
+
+## [2.2.0-beta.5](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.4...v2.2.0-beta.5) (2026-06-23)
+
+
+### Bug Fixes
+
+* lazy imports to prevent torchcodec FFmpeg DLL crash on Windows ([#1089](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1089)) ([2f55377](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/2f55377010fb16c81655aa1c8d08b88daa880797))
+
+## [2.2.0-beta.4](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.3...v2.2.0-beta.4) (2026-06-11)
+
+
+### Bug Fixes
+
+* **nodes:** tolerate doubled-brace JSON output from models like DeepSeek ([#1085](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1085)) ([aaa5d2c](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/aaa5d2cf6d2657f8e8a3b9020ab8b40cdb311c46))
+
+## [2.2.0-beta.3](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.2...v2.2.0-beta.3) (2026-06-01)
+
+
+### Bug Fixes
+
+* **nodes:** update outdated ChatOllama import path to langchain_ollama ([#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076)) ([e6054cb](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/e6054cbf19a7fe940899ea70b30706f676f86fa7))
+
+
+### Docs
+
+* 📚 Standardize and fix links across translated READMEs ([#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074)) ([458d36a](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/458d36a6b83f4a412206cdbe9935a059e9d47f57))
+
+
+### CI
+
+* **release:** 2.1.2 [skip ci] ([210c992](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/210c99280048863774fa27053412185a5c18150d)), closes [#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076) [#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074)
+
+## [2.2.0-beta.2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.1...v2.2.0-beta.2) (2026-06-01)
+
+
 ### Features
 
 * upgrade MiniMax default model to M3 ([#1080](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1080)) ([1b16c26](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/1b16c268f4e9044c1386ccfaf67b38692b487e5a))
@@ -1608,7 +1711,6 @@ Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 
 * implement ScrapeGraph class for only web scraping automation ([612c644](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/612c644623fa6f4fe77a64a5f1a6a4d6cd5f4254))
 * Implement SmartScraperMultiParseMergeFirstGraph class that scrapes a list of URLs and merge the content first and finally generates answers to a given prompt. ([3e3e1b2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/3e3e1b2f3ae8ed803d03b3b44b199e139baa68d4))
-=======
 ## [1.26.7](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.26.6...v1.26.7) (2024-10-19)
 
 
@@ -3682,7 +3784,6 @@ Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 * **release:** 1.6.1 [skip ci] ([44fbd71](https://github.com/VinciGit00/Scrapegraph-ai/commit/44fbd71742a57a4b10f22ed33781bb67aa77e58d))
 
 ## [1.6.1](https://github.com/VinciGit00/Scrapegraph-ai/compare/v1.6.0...v1.6.1) (2024-06-15)
-=======
 
 
 ### Bug Fixes

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scrapegraphai
-Version: 2.1.7
+Version: 2.2.0
 Summary: A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
 Author-email: Marco Vinciguerra <mvincig11@gmail.com>, Lorenzo Padoan <lorenzo.padoan977@gmail.com>
 Keywords: ai,artificial intelligence,gpt,graph,langchain,llm,machine learning,natural language processing,nlp,openai,rag,scrapegraph,scrapegraphai,scraping,web scraping,web scraping library,web scraping tool,webscraping

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "scrapegraphai"
 
-version = "2.1.7"
+version = "2.2.0"
 
 description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
 authors = [

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/scrapegraphai/nodes/generate_answer_node.py

@@ -9,7 +9,6 @@ from typing import List, Optional
 from langchain_core.prompts import PromptTemplate
 from langchain_aws import ChatBedrock
 from langchain_ollama import ChatOllama
-from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.runnables import RunnableParallel
 from langchain_openai import ChatOpenAI
 from requests.exceptions import Timeout
@@ -23,7 +22,10 @@ from ..prompts import (
     TEMPLATE_NO_CHUNKS,
     TEMPLATE_NO_CHUNKS_MD,
 )
-from ..utils.output_parser import get_pydantic_output_parser
+from ..utils.output_parser import (
+    TolerantJsonOutputParser,
+    get_pydantic_output_parser,
+)
 from .base_node import BaseNode
 
 
@@ -148,7 +150,7 @@ class GenerateAnswerNode(BaseNode):
                     format_instructions = ""
         else:
             if not isinstance(self.llm_model, ChatBedrock):
-                output_parser = JsonOutputParser()
+                output_parser = TolerantJsonOutputParser()
                 format_instructions = (
                     "You must respond with a JSON object. Your response should be formatted as a valid JSON "
                     "with a 'content' field containing your analysis. For example:\n"

{scrapegraphai-2.1.7 → scrapegraphai-2.2.0}/scrapegraphai/utils/output_parser.py

@@ -2,13 +2,53 @@
 Functions to retrieve the correct output parser and format instructions for the LLM model.
 """
 
-from typing import Any, Callable, Dict, Type, Union
+from typing import Any, Callable, Dict, List, Type, Union
 
+from langchain_core.exceptions import OutputParserException
+from langchain_core.outputs import Generation
 from langchain_core.output_parsers import JsonOutputParser
 from pydantic import BaseModel as BaseModelV2
 from pydantic.v1 import BaseModel as BaseModelV1
 
 
+def _strip_doubled_braces(text: str) -> str:
+    """Strip one layer of the doubled braces some models echo from the prompt.
+
+    The default ``format_instructions`` show the expected shape using LangChain's
+    escaped braces, e.g. ``{{"content": "..."}}``. Strongly instruction-following
+    models (GPT-4o, etc.) emit single braces, but some models (notably DeepSeek)
+    copy the doubled braces verbatim, producing ``{{"content": "..."}}`` which is
+    not valid JSON. This normalizes that single case and is a no-op otherwise.
+    """
+    stripped = text.strip()
+    if stripped.startswith("{{") and stripped.endswith("}}"):
+        return stripped[1:-1]
+    return text
+
+
+class TolerantJsonOutputParser(JsonOutputParser):
+    """A :class:`JsonOutputParser` tolerant of doubled-brace output.
+
+    Behaviour is unchanged on the happy path: valid JSON is parsed by the parent
+    parser exactly as before. Only when parsing fails AND the output is wrapped in
+    doubled braces (``{{ ... }}``) does it retry once with a single layer of braces
+    removed. This keeps providers like DeepSeek working without altering output for
+    any model that already returns clean JSON.
+    """
+
+    def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
+        try:
+            return super().parse_result(result, partial=partial)
+        except OutputParserException:
+            text = result[0].text
+            normalized = _strip_doubled_braces(text)
+            if normalized != text:
+                return super().parse_result(
+                    [Generation(text=normalized)], partial=partial
+                )
+            raise
+
+
 def get_structured_output_parser(
     schema: Union[Dict[str, Any], Type[BaseModelV1 | BaseModelV2], Type],
 ) -> Callable:

scrapegraphai-2.2.0/tests/utils/output_parser_test.py

@@ -0,0 +1,44 @@
+"""Tests for scrapegraphai.utils.output_parser.TolerantJsonOutputParser."""
+
+import pytest
+
+from scrapegraphai.utils.output_parser import (
+    TolerantJsonOutputParser,
+    _strip_doubled_braces,
+)
+
+
+def test_strip_doubled_braces_unwraps_single_layer():
+    assert _strip_doubled_braces('{{"content": "hi"}}') == '{"content": "hi"}'
+
+
+def test_strip_doubled_braces_is_noop_for_clean_json():
+    text = '{"content": "hi"}'
+    assert _strip_doubled_braces(text) == text
+
+
+def test_strip_doubled_braces_ignores_unbalanced():
+    text = '{{"content": "hi"}'
+    assert _strip_doubled_braces(text) == text
+
+
+def test_tolerant_parser_parses_clean_json_unchanged():
+    parser = TolerantJsonOutputParser()
+    assert parser.parse('{"content": "hi"}') == {"content": "hi"}
+
+
+def test_tolerant_parser_recovers_doubled_braces():
+    """Models such as DeepSeek echo the prompt's escaped braces verbatim."""
+    parser = TolerantJsonOutputParser()
+    assert parser.parse('{{"content": "hi"}}') == {"content": "hi"}
+
+
+def test_tolerant_parser_recovers_doubled_braces_with_whitespace():
+    parser = TolerantJsonOutputParser()
+    assert parser.parse('  {{"content": "hi"}}  ') == {"content": "hi"}
+
+
+def test_tolerant_parser_still_raises_on_irrecoverable_output():
+    parser = TolerantJsonOutputParser()
+    with pytest.raises(Exception):
+        parser.parse("this is not json at all")