aiprose 爬虫成功

README.md

@@ -1,28 +1,3 @@
-# Introduction
-
-An implementation of the standard WordPress API methods is provided,Use the [https://github.com/kolo/xmlrpc](https://github.com/kolo/xmlrpc) library as client.
-
-# Todo List
-- [x] [wp.newPost](#wp.newPost)
-- [ ] wp.getPost
-- [ ] wp.getPosts
-- [ ] wp.editPost
-- [ ] wp.deletePost
-
-# Usage
-- ### wp.newPost
-    ```go
-    c, err := xmlrpc.NewClient(`https://example.com/xmlrpc.php`, xmlrpc.UserInfo{
-		`your username`,
-		`your password`,
-	})
-	if err != nil {
-		log.Fatalln(err)
-	}
-	p := wordpress.NewPost(`content`, `title`, []string{`tag1`, `tag2`}, []string{`cate1`, `cate2`})
-	blogID, err := c.Call(p)
-	if err != nil {
-		log.Println(err)
-	}
-	log.Println(blogID)
-    ```
+| 方法 | 网址 |用户名|
+| :---: | :---: |:---: |
+| SpiderAiprose | https://www.aiprose.com/blogs | nelson |

spider/spider.go

@@ -8,18 +8,13 @@ import (
 )
 
 func SpiderAiprose() {
-	c := colly.NewCollector(colly.AllowedDomains("www.aiprose.com"))
-	//c := colly.NewCollector()
-	c.Async = true
-	// Find and visit all links
+	c := colly.NewCollector(colly.AllowedDomains("www.aiprose.com"), colly.Async(true))
 	c.OnHTML(".home-content-title a[href]", func(e *colly.HTMLElement) {
 		e.Request.Visit(e.Attr("href"))
 	})
-
 	c.OnHTML(".pagination .next a[href]", func(e *colly.HTMLElement) {
 		e.Request.Visit(e.Attr("href"))
 	})
-
 	c.OnHTML(".blog-root", func(e *colly.HTMLElement) {
 		title := strings.TrimSpace(e.DOM.Find(".blog-title").Eq(0).Text())
 		//author:=strings.TrimSpace(e.DOM.Find(".author-info a").Eq(0).Text())
@@ -31,15 +26,11 @@ func SpiderAiprose() {
 			tags = append(tags, htmlquery.InnerText(node))
 		}
 		saveBlog(title, content, time, tags)
-		//println(title +author+ time)
 	})
-
 	c.OnRequest(func(r *colly.Request) {
 		fmt.Println("Visiting", r.URL)
 	})
-
 	c.UserAgent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36"
 	c.Visit("https://www.aiprose.com/blogs")
-	//c.Visit("https://www.aiprose.com/blog/139")
 	c.Wait()
 }