Pre/beta

.github/workflows/pylint.yml

@@ -9,15 +9,15 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - name: Install the latest version of rye
-        uses: eifinger/setup-rye@v3
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
       - name: Install dependencies
-        run: rye sync --no-lock
+        run: uv sync --frozen
       - name: Analysing the code with pylint
-        run: rye run pylint-ci
+        run: uv run poe pylint-ci
       - name: Check Pylint score
         run: |
-          pylint_score=$(rye run pylint-score-ci | grep 'Raw metrics' | awk '{print $4}')
+          pylint_score=$(uv run poe pylint-score-ci | grep 'Raw metrics' | awk '{print $4}')
           if (( $(echo "$pylint_score < 8" | bc -l) )); then
             echo "Pylint score is below 8. Blocking commit."
             exit 1

.github/workflows/release.yml

@@ -14,8 +14,8 @@ jobs:
         run: |
           sudo apt update
           sudo apt install -y git
-      - name: Install the latest version of rye
-        uses: eifinger/setup-rye@v3
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
       - name: Install Node Env
         uses: actions/setup-node@v4
         with:
@@ -27,8 +27,8 @@ jobs:
           persist-credentials: false
       - name: Build app
         run: |
-          rye sync --no-lock
-          rye build
+          uv sync --frozen
+          uv build
         id: build_cache
         if: success()
       - name: Cache build

CHANGELOG.md

@@ -1,3 +1,37 @@
+## [1.32.0-beta.4](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.32.0-beta.3...v1.32.0-beta.4) (2024-12-02)
+
+
+### Features
+
+* add api integration ([8aa9103](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/8aa9103f02af92d9e1a780450daa7bb303afc150))
+* add sdk integration ([209b445](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/209b4456fd668d9d124fd5586b32a4be677d4bf8))
+
+
+### chore
+
+* migrate from rye to uv ([5fe528a](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/5fe528a7e7a3e230d8f68fd83ce5ad6ede5adfef))
+
+## [1.32.0-beta.3](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.32.0-beta.2...v1.32.0-beta.3) (2024-11-26)
+
+
+### Bug Fixes
+
+* improved links extraction for parse_node, resolves [#822](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/822) ([7da7bfe](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/7da7bfe338a6ce53c83361a1f6cd9ea2d5bd797f))
+
+## [1.32.0-beta.2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.32.0-beta.1...v1.32.0-beta.2) (2024-11-25)
+
+
+### Bug Fixes
+
+* error on fetching the code ([7285ab0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/7285ab065bba9099ba2751c9d2f21ee13fed0d5f))
+
+## [1.32.0-beta.1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.31.1...v1.32.0-beta.1) (2024-11-24)
+
+
+### Features
+
+* revert search function ([faf0c01](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/faf0c0123b5e2e548cbd1917e9d1df22e1edb1c5))
+
 ## [1.31.1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.31.0...v1.31.1) (2024-11-22)
 
 

examples/scrapegraph-api/smart_scraper_api.py

@@ -0,0 +1,44 @@
+""" 
+Basic example of scraping pipeline using SmartScraper
+"""
+import os
+import json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import SmartScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+
+load_dotenv()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+
+graph_config = {
+    "llm": {
+        "model": "scrapegraphai/smart-scraper",
+        "api_key": os.getenv("SCRAPEGRAPH_API_KEY")
+    },
+    "verbose": True,
+    "headless": False,
+}
+
+# ************************************************
+# Create the SmartScraperGraph instance and run it
+# ************************************************
+
+smart_scraper_graph = SmartScraperGraph(
+    prompt="Extract me all the articles",
+    source="https://www.wired.com",
+    config=graph_config
+)
+
+result = smart_scraper_graph.run()
+print(json.dumps(result, indent=4))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = smart_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))

pyproject.toml

@@ -3,7 +3,7 @@ name = "scrapegraphai"
 
 
 
-version = "1.31.1"
+version = "1.32.0b4"
 
 
 
@@ -43,7 +43,8 @@ dependencies = [
     "transformers>=4.44.2",
     "googlesearch-python>=1.2.5",
     "simpleeval>=1.0.0",
-    "async_timeout>=4.0.3"
+    "async_timeout>=4.0.3",
+    "scrapegraph-py>=0.0.4"
 ]
 
 license = "MIT"
@@ -91,7 +92,7 @@ other-language-models = [
     "langchain-anthropic>=0.1.11",
     "langchain-huggingface>=0.0.3",
     "langchain-nvidia-ai-endpoints>=0.1.6",
-    "langchain_together>=1.2.9"
+    "langchain_together>=0.2.0"
 ]
 
 # Group 2: More Semantic Options
@@ -116,17 +117,21 @@ screenshot_scraper = [
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
-[tool.rye]
-managed = true
+[dependency-groups]
+dev = [
+    "burr[start]==0.22.1",
+    "sphinx==6.0",
+    "furo==2024.5.6",
+]
+
+[tool.uv]
 dev-dependencies = [
+    "poethepoet>=0.31.1",
     "pytest==8.0.0",
     "pytest-mock==3.14.0",
-    "-e file:.[burr]",
-    "-e file:.[docs]",
     "pylint>=3.2.5",
 ]
 
-[tool.rye.scripts]
-pylint-local = "pylint scrapegraphai/**/*.py"
+[tool.poe.tasks]
+pylint-local = "pylint scraperaphai/**/*.py"
 pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py"
-update-requirements = "python 'manual deployment/autorequirements.py'"

requirements-dev.lock

@@ -353,7 +353,7 @@ pyasn1==0.6.0
     # via rsa
 pyasn1-modules==0.4.0
     # via google-auth
-pydantic==2.8.2
+pydantic==2.10.1
     # via burr
     # via fastapi
     # via fastapi-pagination
@@ -368,7 +368,8 @@ pydantic==2.8.2
     # via openai
     # via pydantic-settings
     # via qdrant-client
-pydantic-core==2.20.1
+    # via scrapegraph-py
+pydantic-core==2.27.1
     # via pydantic
 pydantic-settings==2.5.2
     # via langchain-community
@@ -396,6 +397,7 @@ python-dateutil==2.9.0.post0
     # via pandas
 python-dotenv==1.0.1
     # via pydantic-settings
+    # via scrapegraph-py
     # via scrapegraphai
 pytz==2024.1
     # via pandas
@@ -424,6 +426,7 @@ requests==2.32.3
     # via langchain-community
     # via langsmith
     # via mistral-common
+    # via scrapegraph-py
     # via sphinx
     # via streamlit
     # via tiktoken
@@ -439,6 +442,8 @@ s3transfer==0.10.2
     # via boto3
 safetensors==0.4.5
     # via transformers
+scrapegraph-py==0.0.3
+    # via scrapegraphai
 semchunk==2.2.0
     # via scrapegraphai
 sentencepiece==0.2.0

requirements.lock

@@ -257,7 +257,7 @@ pyasn1==0.6.0
     # via rsa
 pyasn1-modules==0.4.0
     # via google-auth
-pydantic==2.8.2
+pydantic==2.10.1
     # via google-generativeai
     # via langchain
     # via langchain-aws
@@ -269,7 +269,8 @@ pydantic==2.8.2
     # via openai
     # via pydantic-settings
     # via qdrant-client
-pydantic-core==2.20.1
+    # via scrapegraph-py
+pydantic-core==2.27.1
     # via pydantic
 pydantic-settings==2.5.2
     # via langchain-community
@@ -286,6 +287,7 @@ python-dateutil==2.9.0.post0
     # via pandas
 python-dotenv==1.0.1
     # via pydantic-settings
+    # via scrapegraph-py
     # via scrapegraphai
 pytz==2024.1
     # via pandas
@@ -313,6 +315,7 @@ requests==2.32.3
     # via langchain-community
     # via langsmith
     # via mistral-common
+    # via scrapegraph-py
     # via tiktoken
     # via transformers
 rpds-py==0.20.0
@@ -324,6 +327,8 @@ s3transfer==0.10.2
     # via boto3
 safetensors==0.4.5
     # via transformers
+scrapegraph-py==0.0.3
+    # via scrapegraphai
 semchunk==2.2.0
     # via scrapegraphai
 sentencepiece==0.2.0

scrapegraphai/docloaders/chromium.py

@@ -100,18 +100,11 @@ async def ascrape_undetected_chromedriver(self, url: str) -> str:
     async def ascrape_playwright(self, url: str) -> str:
         """
         Asynchronously scrape the content of a given URL using Playwright's async API.
-
-        Args:
-            url (str): The URL to scrape.
-
-        Returns:
-            str: The scraped HTML content or an error message if an exception occurs.
         """
         from playwright.async_api import async_playwright
         from undetected_playwright import Malenia
 
         logger.info(f"Starting scraping with {self.backend}...")
-        results = ""
         attempt = 0
 
         while attempt < self.RETRY_LIMIT:
@@ -127,16 +120,15 @@ async def ascrape_playwright(self, url: str) -> str:
                     await page.wait_for_load_state(self.load_state)
                     results = await page.content()
                     logger.info("Content scraped")
-                    break
+                    return results
             except (aiohttp.ClientError, asyncio.TimeoutError, Exception) as e:
                 attempt += 1
                 logger.error(f"Attempt {attempt} failed: {e}")
                 if attempt == self.RETRY_LIMIT:
-                    results = f"Error: Network error after {self.RETRY_LIMIT} attempts - {e}"
+                    raise RuntimeError(f"Failed to fetch {url} after {self.RETRY_LIMIT} attempts: {e}")
             finally:
-                await browser.close()
-
-        return results
+                if 'browser' in locals():
+                    await browser.close()
 
     async def ascrape_with_js_support(self, url: str) -> str:
         """

scrapegraphai/graphs/smart_scraper_graph.py

@@ -13,6 +13,7 @@
     ConditionalNode
 )
 from ..prompts import REGEN_ADDITIONAL_INFO
+from scrapegraph_py import SyncClient
 
 class SmartScraperGraph(AbstractGraph):
     """
@@ -59,6 +60,15 @@ def _create_graph(self) -> BaseGraph:
         Returns:
             BaseGraph: A graph instance representing the web scraping workflow.
         """
+        if self.llm_model == "scrapegraphai/smart-scraper":
+
+            sgai_client = SyncClient(api_key=self.config.get("api_key"))
+
+            response = sgai_client.smartscraper(
+                website_url=self.source,
+                user_prompt=self.prompt
+            )
+            return response
 
         fetch_node = FetchNode(
             input="url| local_dir",