adding corporate data to webscraper

This commit is contained in:
2025-11-21 00:17:59 +01:00
parent 0ea3fcc3b5
commit 9d0d15f3f8
18 changed files with 2128 additions and 970 deletions

View File

@@ -1,14 +1,40 @@
[package]
name = "WebScraper"
name = "event_backtest_engine"
version = "0.1.0"
edition = "2024"
edition = "2021"
authors = ["Your Name <you@example.com>"]
description = "High-impact economic & corporate earnings data collector for short-event backtesting (overnight/weekend gaps)"
license = "MIT OR Apache-2.0"
repository = "https://github.com/yourname/event_backtest_engine"
keywords = ["finance", "earnings", "economic-calendar", "backtesting", "quant"]
categories = ["finance", "data-structures", "asynchronous"]
# ===================================================================
# Dependencies
# ===================================================================
[dependencies]
fantoccini = { version = "0.21.5", default-features = false, features = ["native-tls"] }
tokio = { version = "1", features = ["full"] }
serde = { version = "1", features = ["derive"] }
anyhow = "1.0"
futures = "0.3"
# Async runtime
tokio = { version = "1.38", features = ["full"] }
# Web scraping & HTTP
reqwest = { version = "0.12", features = ["json", "gzip", "brotli", "deflate"] }
scraper = "0.19" # HTML parsing for Yahoo earnings pages
fantoccini = { version = "0.20", features = ["rustls-tls"] } # Headless Chrome for finanzen.net
# Serialization
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
chrono = "0.4.42"
regex = "1.0"
# Date & time
chrono = { version = "0.4", features = ["serde"] }
# Error handling
anyhow = "1.0"
# Logging (optional but recommended)
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
# Parallel processing (for batch tickers)
futures = "0.3"
rayon = "1.10" # optional: for parallel price downloads