chore(chrome_intercept): fix host match blocking assets

spider-rs · Dec 15, 2023 · 177da35 · 177da35
1 parent 0f9313a
commit 177da35
Show file tree

Hide file tree

Showing 7 changed files with 21 additions and 21 deletions.
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/examples/Cargo.toml b/examples/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "spider_examples"
-version = "1.70.4"
+version = "1.70.5"
 authors = ["madeindjs <contact@rousseau-alexandre.fr>", "j-mendez <jeff@a11ywatch.com>"]
 description = "Multithreaded web crawler written in Rust."
 repository = "https://github.com/spider-rs/spider"
@@ -22,7 +22,7 @@ htr = "0.5.27"
 flexbuffers = "2.0.0"
 
 [dependencies.spider]
-version = "1.70.4"
+version = "1.70.5"
 path = "../spider"
 features = ["serde"]
 

diff --git a/spider/Cargo.toml b/spider/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "spider"
-version = "1.70.4"
+version = "1.70.5"
 authors = ["madeindjs <contact@rousseau-alexandre.fr>", "j-mendez <jeff@a11ywatch.com>"]
 description = "The fastest web crawler written in Rust."
 repository = "https://github.com/spider-rs/spider"

diff --git a/spider/README.md b/spider/README.md
@@ -16,7 +16,7 @@ This is a basic async example crawling a web page, add spider to your `Cargo.tom
 
 ```toml
 [dependencies]
-spider = "1.70.4"
+spider = "1.70.5"
 ```
 
 And then the code:
@@ -91,7 +91,7 @@ We have a couple optional feature flags. Regex blacklisting, jemaloc backend, gl
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["regex", "ua_generator"] }
+spider = { version = "1.70.5", features = ["regex", "ua_generator"] }
 ```
 
 1. `ua_generator`: Enables auto generating a random real User-Agent.
@@ -126,7 +126,7 @@ Move processing to a worker, drastically increases performance even if worker is
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["decentralized"] }
+spider = { version = "1.70.5", features = ["decentralized"] }
 ```
 
 ```sh
@@ -146,7 +146,7 @@ Use the subscribe method to get a broadcast channel.
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["sync"] }
+spider = { version = "1.70.5", features = ["sync"] }
 ```
 
 ```rust,no_run
@@ -176,7 +176,7 @@ Allow regex for blacklisting routes
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["regex"] }
+spider = { version = "1.70.5", features = ["regex"] }
 ```
 
 ```rust,no_run
@@ -203,7 +203,7 @@ If you are performing large workloads you may need to control the crawler by ena
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["control"] }
+spider = { version = "1.70.5", features = ["control"] }
 ```
 
 ```rust
@@ -273,7 +273,7 @@ Use cron jobs to run crawls continuously at anytime.
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["sync", "cron"] }
+spider = { version = "1.70.5", features = ["sync", "cron"] }
 ```
 
 ```rust,no_run
@@ -312,7 +312,7 @@ the feature flag [`chrome_intercept`] to possibly speed up request using Network
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["chrome", "chrome_intercept"] }
+spider = { version = "1.70.5", features = ["chrome", "chrome_intercept"] }
 ```
 
 You can use `website.crawl_concurrent_raw` to perform a crawl without chromium when needed. Use the feature flag `chrome_headed` to enable headful browser usage if needed to debug.
@@ -343,7 +343,7 @@ Intelligently run crawls using HTTP and JavaScript Rendering when needed. The be
 
 ```toml
 [dependencies]
-spider = { version = "1.70.4", features = ["smart"] }
+spider = { version = "1.70.5", features = ["smart"] }
 ```
 
 ```rust,no_run

diff --git a/spider/src/website.rs b/spider/src/website.rs
@@ -1601,7 +1601,7 @@ impl Website {
                     let ih = task::spawn(async move {
                         while let Some(event) = rp.next().await {
                             let u = &event.request.url;
-                            if ignore_images && ResourceType::Image == event.resource_type || !u.contains(&host_name) && !crate::page::JS_FRAMEWORK_ALLOW.contains(&u.as_str()) {
+                            if ignore_images && ResourceType::Image == event.resource_type || !u.starts_with(&host_name) && !crate::page::JS_FRAMEWORK_ALLOW.contains(&u.as_str()) {
                                 match chromiumoxide::cdp::browser_protocol::fetch::FulfillRequestParams::builder()
                                 .request_id(event.request_id.clone())
                                 .response_code(200)

diff --git a/spider_cli/Cargo.toml b/spider_cli/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "spider_cli"
-version = "1.70.4"
+version = "1.70.5"
 authors = ["madeindjs <contact@rousseau-alexandre.fr>", "j-mendez <jeff@a11ywatch.com>"]
 description = "The fastest web crawler CLI written in Rust."
 repository = "https://github.com/spider-rs/spider"
@@ -26,7 +26,7 @@ quote = "1.0.18"
 failure_derive = "0.1.8"
 
 [dependencies.spider]
-version = "1.70.4"
+version = "1.70.5"
 path = "../spider"
 
 [[bin]]

diff --git a/spider_worker/Cargo.toml b/spider_worker/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "spider_worker"
-version = "1.70.4"
+version = "1.70.5"
 authors = ["madeindjs <contact@rousseau-alexandre.fr>", "j-mendez <jeff@a11ywatch.com>"]
 description = "The fastest web crawler as a worker or proxy."
 repository = "https://github.com/spider-rs/spider"
@@ -22,7 +22,7 @@ lazy_static = "1.4.0"
 env_logger = "0.10.0"
 
 [dependencies.spider]
-version = "1.70.4"
+version = "1.70.5"
 path = "../spider"
 features = ["serde", "flexbuffers"]