From 0d6494d164cc490d62473eae0fbd79d5573bb380 Mon Sep 17 00:00:00 2001
From: Philipp Tanlak <philipp.tanlak@gmail.com>
Date: Wed, 7 Feb 2024 23:20:55 +0100
Subject: Add retry module and change rate to requests per minute (#37)

---
 template.js | 74 ++++++++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 56 insertions(+), 18 deletions(-)

(limited to 'template.js')

diff --git a/template.js b/template.js
index a7a510f..17fe6ba 100644
--- a/template.js
+++ b/template.js
@@ -1,27 +1,65 @@
 export const config = {
-  url: "https://news.ycombinator.com/", // Specify the URL to start scraping from.
-  // depth: 0,                          // Specify how deep links should be followed.  (default = 0, no follow)
-  // allowedDomains: [],                // Specify the allowed domains. ['*'] for all. (default = domain from url)
-  // blockedDomains: [],                // Specify the blocked domains.                (default = none)
-  // allowedURLs: [],                   // Specify the allowed URLs as regex.          (default = all allowed)
-  // blockedURLs: [],                   // Specify the blocked URLs as regex.          (default = non blocked)
-  // rate: 100,                         // Specify the rate in requests per second.    (default = 100)
-  // cache: "file",                     // Enable file-based request caching.          (default = no cache)
+    // Specify the URL to start scraping from.
+    url: "https://example.com/",
+
+    // Specify the multiple URLs to start scraping from.   (default = [])
+    // urls: [                          
+    //     "https://anothersite.com/",
+    //     "https://yetanother.com/",
+    // ],
+
+    // Specify how deep links should be followed.          (default = 0, no follow)
+    // depth: 5,                        
+
+    // Speficy the css selectors to follow.                (default = ["a[href]"])
+    // follow: [".next > a", ".related a"],                      
+ 
+    // Specify the allowed domains. ['*'] for all.         (default = domain from url)
+    // allowedDomains: ["example.com", "anothersite.com"],              
+ 
+    // Specify the blocked domains.                        (default = none)
+    // blockedDomains: ["somesite.com"],              
+
+    // Specify the allowed URLs as regex.                  (default = all allowed)
+    // allowedURLs: ["/posts", "/articles/\d+"],                 
+ 
+    // Specify the blocked URLs as regex.                  (default = none)
+    // blockedURLs: ["/admin"],                 
+   
+    // Specify the rate in requests per minute.            (default = no rate limit)
+    // rate: 60,                       
+
+    // Specify the number of concurrent requests.          (default = no limit)
+    // concurrency: 1,                       
+
+    // Specify a single HTTP(S) proxy URL.                 (default = no proxy)
+    // proxy: "http://someproxy.com:8043",
+
+    // Specify multiple HTTP(S) proxy URLs.                (default = no proxy)
+    // proxies: [
+    //   "http://someproxy.com:8043",
+    //   "http://someotherproxy.com:8043",
+    // ],                     
+
+    // Enable file-based request caching.                  (default = no cache)
+    // cache: "file",                   
+
+    // Specify the HTTP request header.                    (default = none)
+    // headers: {                       
+    //     "Authorization": "Bearer ...",
+    //     "User-Agent": "Mozilla ...",
+    // },
 };
 
 export default function({ doc, absoluteURL }) {
-  const title = doc.find("title");
-  const posts = doc.find(".athing");
+  const title = doc.find("h1");
+  const link = doc.find("a");
 
   return {
     title: title.text(),
-    posts: posts.map((post) => {
-      const link = post.find(".titleline > a");
-
-      return {
-        title: link.text(),
-        url: absoluteURL(link.attr("href")),
-      };
-    }),
+    link: {
+      text: link.text(),
+      url: absoluteURL(link.attr("href")),
+    },
   };
 }
-- 
cgit v1.2.3