Initial commit

devops · devops · commit e7c336a3c9e0 · 2016-05-04T08:51:53.000+08:00
diff --git a/README.md b/README.md
@@ -0,0 +1,3 @@
+# 慕课网 Python开发简单爬虫 实例代码
+
+
diff --git a/__init__.py b/__init__.py
diff --git a/html_downloader.py b/html_downloader.py
@@ -0,0 +1,14 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+import urllib2
+
+
+class HtmlDownloader(object):
+
+    def download(self, url):
+        if url is None:
+            return None
+        response = urllib2.urlopen(url)
+        if response.getcode() != 200:
+            return None
+        return response.read()
diff --git a/html_outputer.py b/html_outputer.py
@@ -0,0 +1,29 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+class HtmlOutputer(object):
+
+    def __init__(self):
+        self.datas = []
+
+
+    def collect_data(self, data):
+        if data is None:
+            return
+        self.datas.append(data)
+
+    def output_html(self):
+        fout = open('output.html', 'w')
+        fout.write("<html>")
+        fout.write("<body>")
+        fout.write("<table>")
+
+        for data in self.datas:
+            fout.write("<tr>")
+            fout.write("<td>%s</td>" % data['url'])
+            fout.write("<td>%s</td>" % data['title'].encode('utf-8'))
+            fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
+            fout.write("</tr>")
+        fout.write("</table>")
+        fout.write("</body>")
+        fout.write("</html>")
+        fout.close()
diff --git a/html_parser.py b/html_parser.py
@@ -0,0 +1,42 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+import re
+import urlparse
+
+from bs4 import BeautifulSoup
+
+
+class HtmlParser(object):
+
+    def parse(self, page_url, html_cont):
+        if page_url is None or html_cont is None:
+            return
+
+        soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
+        new_urls = self._get_new_urls(page_url, soup)
+        new_data = self._get_new_data(page_url, soup)
+        return new_urls, new_data
+
+    def _get_new_urls(self, page_url, soup):
+        new_urls = set()
+        links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
+        for link in links:
+            new_url = link['href']
+            new_full_url = urlparse.urljoin(page_url, new_url)
+            new_urls.add(new_full_url)
+        return new_urls
+
+
+    def _get_new_data(self, page_url, soup):
+        res_data = {}
+
+        # url
+
+        res_data['url'] = page_url
+        # <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
+        title_node = soup.find('dd', class_= "lemmaWgt-lemmaTitle-title").find("h1")
+        res_data['title'] = title_node.get_text()
+
+        summary_node = soup.find('div', class_="lemma-summary")
+        res_data['summary'] = summary_node.get_text()
+        return res_data
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,2 @@
+beautifulsoup4==4.4.1
+wheel==0.24.0
diff --git a/spider_main.py b/spider_main.py
@@ -0,0 +1,69 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+
+# 爬虫调度端
+
+## URL管理器
+
+### 添加新的URL到待爬取集合中
+### 判断待添加URL是否在容器中
+### 获取待爬取URL
+### 判断是否还有待爬取URL
+### 将URL从待爬取移动到已爬取
+
+## 网页下载器
+### urllib2
+### requests
+
+## 网页解析器
+
+### 正则表达式
+### html.parser
+### BeautifulSoup
+### lxml
+
+
+## 分析目标
+### URL格式
+### 数据格式
+### 网页编码
+
+
+from baike_spider import url_manager, html_downloader, html_outputer, html_parser
+
+
+class SpiderMain(object):
+
+    def __init__(self):
+        self.urls = url_manager.UrlManager()
+        self.downloader = html_downloader.HtmlDownloader()
+        self.parser = html_parser.HtmlParser()
+        self.outputer = html_outputer.HtmlOutputer()
+
+
+
+    def craw(self, root_url):
+        count = 1
+        self.urls.add_new_url(root_url)
+        while self.urls.has_new_url():
+            try :
+                new_url = self.urls.get_new_url()
+                print 'craw %d : %s' % (count, new_url)
+                html_cont = self.downloader.download(new_url)
+                new_urls, new_data = self.parser.parse(new_url, html_cont)
+                self.urls.add_new_urls(new_urls)
+                self.outputer.collect_data(new_data)
+
+
+                if count == 1000:
+                    break
+                count = count + 1
+            except:
+                print 'craw failed'
+
+        self.outputer.output_html()
+
+if __name__ == "__main__":
+    root_url = "http://baike.baidu.com/view/21087.htm"
+    obj_spider = SpiderMain()
+    obj_spider.craw(root_url)
diff --git a/url_manager.py b/url_manager.py
@@ -0,0 +1,30 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+class UrlManager(object):
+    def __init__(self):
+        self.new_urls = set()
+        self.old_urls = set()
+
+    def add_new_url(self, url):
+        if url is None:
+            return
+        if url not in self.new_urls and url not in self.old_urls:
+            self.new_urls.add(url)
+
+    def add_new_urls(self, urls):
+        if urls is None or len(urls) == 0:
+            return
+        for url in urls:
+            self.add_new_url(url)
+
+    def has_new_url(self):
+        return len(self.new_urls) != 0
+
+
+    def get_new_url(self):
+        new_url = self.new_urls.pop()
+        self.old_urls.add(new_url)
+        return new_url
+
+
+

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+# 慕课网 Python开发简单爬虫实例代码`
	`2`	`+`
	`3`	`+`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+beautifulsoup4==4.4.1`
	`2`	`+wheel==0.24.0`