完成正文提取和基本的html解析

.gitignore

@@ -0,0 +1 @@
+/vendor

README.md

@@ -1,2 +1,2 @@
 # readability
-Developed from https://github.com/feelinglucky/php-readability
+Automatic article content extraction from html.

composer.json

@@ -0,0 +1,23 @@
+{
+    "name": "vanry/readability",
+    "description": "Automatic article content extraction from html and html parser.",
+    "keywords": ["readability", "extraction", "html", "parser"],
+    "type": "library",
+    "license": "MIT",
+    "minimum-stability": "dev",
+    "homepage": "http://vanry.me",
+    "authors": [
+        {
+            "name": "vanry",
+            "email": "[email protected]"
+        }
+    ],
+    "require": {
+        "php": ">=5.4"
+    },
+    "autoload": {
+        "psr-4": {
+            "Readability\\": "src/"
+        }
+    }
+}

demo.php

@@ -0,0 +1,20 @@
+<?php
+
+require 'vendor/autoload.php';
+
+$url = 'http://sports.sina.com.cn/basketball/nba/2016-11-05/doc-ifxxnety7387922.shtml';
+
+$html = file_get_contents($url);
+
+$readability = new Readability\Readability($html);
+
+// $readability->load($html);
+
+echo 'Title: '.$readability->title().PHP_EOL;
+echo 'Date: '.$readability->date().PHP_EOL;
+echo 'Text: '.$readability->text().PHP_EOL;
+echo 'Content: '.$readability->content().PHP_EOL;
+echo 'WordCount: '.$readability->wordCount().PHP_EOL;
+
+// image source
+print_r($readability->images());