1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
//! A crate to asynchronously crawl web pages. This crate was largely inspired by the python module
//! `scrapy`, but updated to take advantage of Rust's safety, performance, and expressiveness.
//!
//! # About
//! This crate is built around the idea of transforming HTTP responses into scraped `Items`
//! through dynamically linked handlers. The caller defines the handlers and the crate takes care
//! of the scheduling.
//!
//! # Basic Example
//!
//!The following example shows the most basic handler chain possible:
//!
//! ```no_run
//! // Needed for the yield keyword to work
//! #![feature(generators)]
//!
//! use futures::stream::StreamExt; // Provides friendly methods for streams
//! use reqwest::{Client, Response};
//! use scrappy_do::{handle, wrap};
//! use url::Url;
//!
//! // This is what we are trying to create from the web pages
//! #[derive(Debug)]
//! struct SomeItem;
//!
//! // This tracks metadata we find useful during scraping.
//! #[derive(Debug)]
//! struct SomeContext;
//!
//! #[handle(item = SomeItem)]
//! fn handler_foo(
//! client: Client,
//! response: Response,
//! context: SomeContext,
//! ) {
//!
//! // Process the response....
//!
//! // Return some scraped item
//! yield SomeItem;
//! }
//!
//! // Sets up multithreaded runtime
//! #[tokio::main]
//! async fn main() {
//! // Build the HTTP client
//! let client = reqwest::Client::builder()
//! .build()
//! .unwrap();
//!
//! // Build the spider
//! let spider = scrappy_do::Spider::new(client.clone());
//!
//! let items = spider
//! // A web requires an initial address, handler, and context in order to be created. All
//! // other configuration is optional.
//! .web()
//! .start(
//! client
//! .get(Url::parse("http://somedomain.toscrape.com").unwrap())
//! .build()
//! .unwrap(),
//! )
//! .handler(wrap!(handler_foo))
//! .context(SomeContext)
//! .build()
//! .crawl()
//! .await;
//!
//! // The stream must be pinned to the stack to iterate over it
//! tokio::pin!(items);
//!
//! // Process the items scraped.
//! while let Some(item) = items.next().await {
//! println!("{:?}", item);
//! }
//! }
//! ```
//!
//! # Chaining Example
//!
//! This example shows a slightly more complicated chain where a handler invokes another handler.
//! The important thing to note is that the caller doesn't change the inital chain invocation at all.
//!
//! ```no_run
//! // Needed for the yield keyword to work
//! #![feature(generators)]
//!
//! use futures::stream::StreamExt; // Provides friendly methods for streams
//! use reqwest::{Client, Response};
//! use scrappy_do::{handle, wrap};
//! use url::Url;
//!
//! // This is what we are trying to create from the web pages
//! #[derive(Debug)]
//! struct SomeItem;
//!
//! // This tracks metadata we find useful during scraping.
//! #[derive(Debug)]
//! struct SomeContext;
//!
//!// The inital handler
//! #[handle(item = SomeItem)]
//! fn handler_foo(
//! client: Client,
//! response: Response,
//! context: SomeContext,
//! ) {
//!
//! // Process the response....
//!
//! let callback = scrappy_do::Callback::new(
//! wrap!(handler_bar),
//! client
//! .get(response.url().clone())
//! .build()
//! .unwrap(),
//! context,
//! );
//!
//! // Chain the next callback
//! yield callback;
//!
//! // Return some scraped item
//! yield SomeItem;
//! }
//!
//! // Called by handler_foo
//! #[handle(item = SomeItem)]
//! fn handler_bar(
//! client: Client,
//! response: Response,
//! context: SomeContext,
//! ) {
//!
//! // Process the response....
//!
//! // Return some scraped item
//! yield SomeItem;
//! }
//!
//! // Sets up multithreaded runtime
//! #[tokio::main]
//! async fn main() {
//! // Build the HTTP client
//! let client = reqwest::Client::builder()
//! .build()
//! .unwrap();
//!
//! // Build the spider
//! let spider = scrappy_do::Spider::new(client.clone());
//!
//! let items = spider
//! // A web requires an initial address, handler, and context in order to be created. All
//! // other configuration is optional.
//! .web()
//! .start(
//! client
//! .get(Url::parse("http://somedomain.toscrape.com").unwrap())
//! .build()
//! .unwrap(),
//! )
//! .handler(wrap!(handler_foo))
//! .context(SomeContext)
//! .build()
//! .crawl()
//! .await;
//!
//! // The stream must be pinned to the stack to iterate over it
//! tokio::pin!(items);
//!
//! // Process the items scraped.
//! while let Some(item) = items.next().await {
//! println!("{:?}", item);
//! }
//! }
//! ```
//!
//! Ultimately the chain can be as complicated or as simple as the caller wants. It can even be
//! never ending if need be and the `Web` will just keep happily chugging along processing
//! handlers.
//!
pub use scrappy_do_codegen::*;
mod callback;
mod handler;
mod spider;
pub mod util;
pub use callback::{Callback, Indeterminate};
pub use handler::{Handler, HandlerImpl};
pub use spider::{Spider, Web, WebBuilder};
#[doc(hidden)]
pub use tokio::{
spawn,
sync::mpsc::{channel, Receiver},
};