ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README

Browse Source
This commit is contained in:
UncleCode
2025-04-23 19:50:33 +08:00
parent 37fd80e4b9
commit 146f9d415f
2 changed files with 45 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
README.md
View File

@@ -523,8 +523,33 @@ async def test_news_crawl():
- **📊 Table-to-DataFrame Extraction**: Extract HTML tables directly to CSV or pandas DataFrames: - **📊 Table-to-DataFrame Extraction**: Extract HTML tables directly to CSV or pandas DataFrames:
```python ```python
crawler_config = CrawlerRunConfig(extract_tables=True) crawler = AsyncWebCrawler(config=browser_config)
# Access tables via result.tables or result.tables_as_dataframe await crawler.start()
try:
# Set up scraping parameters
crawl_config = CrawlerRunConfig(
table_score_threshold=8, # Strict table detection
)
# Execute market data extraction
results: List[CrawlResult] = await crawler.arun(
url="https://coinmarketcap.com/?page=1", config=crawl_config
)
# Process results
raw_df = pd.DataFrame()
for result in results:
if result.success and result.media["tables"]:
raw_df = pd.DataFrame(
result.media["tables"][0]["rows"],
columns=result.media["tables"][0]["headers"],
)
break
print(raw_df.head())
finally:
await crawler.stop()
``` ```
- **🚀 Browser Pooling**: Pages launch hot with pre-warmed browser instances for lower latency and memory usage - **🚀 Browser Pooling**: Pages launch hot with pre-warmed browser instances for lower latency and memory usage
@@ -544,7 +569,7 @@ async def test_news_crawl():
claude mcp add --transport sse c4ai-sse http://localhost:11235/mcp/sse claude mcp add --transport sse c4ai-sse http://localhost:11235/mcp/sse
``` ```
- **🖥️ Interactive Playground**: Test configurations and generate API requests with the built-in web interface at `/playground` - **🖥️ Interactive Playground**: Test configurations and generate API requests with the built-in web interface at `http://localhost:11235//playground`
- **🐳 Revamped Docker Deployment**: Streamlined multi-architecture Docker image with improved resource efficiency - **🐳 Revamped Docker Deployment**: Streamlined multi-architecture Docker image with improved resource efficiency

34
docs/examples/crypto_analysis_example.py
View File

@@ -383,29 +383,29 @@ async def main():
scroll_delay=0.2, scroll_delay=0.2,
) )
# # Execute market data extraction # Execute market data extraction
# results: List[CrawlResult] = await crawler.arun( results: List[CrawlResult] = await crawler.arun(
# url="https://coinmarketcap.com/?page=1", config=crawl_config url="https://coinmarketcap.com/?page=1", config=crawl_config
# ) )
# # Process results # Process results
# raw_df = pd.DataFrame() raw_df = pd.DataFrame()
# for result in results: for result in results:
# if result.success and result.media["tables"]: if result.success and result.media["tables"]:
# # Extract primary market table # Extract primary market table
# # DataFrame # DataFrame
# raw_df = pd.DataFrame( raw_df = pd.DataFrame(
# result.media["tables"][0]["rows"], result.media["tables"][0]["rows"],
# columns=result.media["tables"][0]["headers"], columns=result.media["tables"][0]["headers"],
# ) )
# break break
# This is for debugging only # This is for debugging only
# ////// Remove this in production from here.. # ////// Remove this in production from here..
# Save raw data for debugging # Save raw data for debugging
# raw_df.to_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv", index=False) raw_df.to_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv", index=False)
# print("🔍 Raw data saved to 'raw_crypto_data.csv'") print("🔍 Raw data saved to 'raw_crypto_data.csv'")
# Read from file for debugging # Read from file for debugging
raw_df = pd.read_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv") raw_df = pd.read_csv(f"{__current_dir__}/tmp/raw_crypto_data.csv")