网络爬虫

Posted on |

依赖BeautifulSoup Python

主文件spider_main.py


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
# -*- coding:utf-8 -*-
# 主程序,负责根url，以及启动爬虫
 import html_downloder
 import html_output
 import html_parser
 import url_manager


class SpilderMain:
    def __init__(self):
        # 初始化所需要的对象,包括url管理器，网页下载器，网页解析器，输出器
        # 来提供给craw（）使用
        # 来提供给craw（）使用
        self.urls = url_manager.UrlManager()
        self.downloader = html_downloder.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_output.HtmlOutputer()

    def craw(self, url):
        count = 1   # url计数
        # 添加根url
        self.urls.add_new_url(url)
        # 开始解析
        while self.urls.has_new_url():
            try:
                # 获取url
                new_url = self.urls.get_new_url()
                print("第%d个url：%s" % (count, new_url))
                # 将url对应的页面进行下载
                html_cont = self.downloader.download(new_url)
                # 对下载下来的页面进行解析,将解析出来的数据进行保存
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                # 将解析出来的urls添加到url_manager
                self.urls.add_new_urls(new_urls)
                # 将数据进行收集
                self.outputer.collect_data(new_data)

                if count == 15:
                    break
                count += 1
            except:
                print("爬取失败")

        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpilderMain()
    # 启动爬虫
    obj_spider.craw(root_url)

网页下载器html_downloder.py


1
2
3
4
5
6
7
8
9
10
11
12
13
14
# -*- coding:utf-8 -*-
# 页面下载器
import urllib.request


class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return None
        response = urllib.request.urlopen(url)
        if response.getcode() != 200:
            return None
        return response.read()
#页面下载器

网页解析器html_parser.py 


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
# -*- coding:utf-8 -*-
# 网页解析器
import re
from bs4 import BeautifulSoup
import urllib.parse


class HtmlParser(object):
    # 对html_cont的内容进行解析
    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

    # 获取页面上所有的url
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        # 根据分析，链接的格式是：/view/12334.htm
        links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
        for link in links:
            new_url = link['href']
            # url格式需要进行拼接，加上  http://baike.baidu.com
            new_full_url = urllib.parse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        return new_urls

    # 获取每一页面的数据，包括标题以及简介
    def _get_new_data(self, page_url, soup):
        # 以一个词典数据类型保存数据
        res_data = {}
        # 保存url
        res_data['url'] = page_url
        # 下面是标题的格式
        # <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()
        # 开始获取简介的内容
        # <div class="lemma-summary" label-module="lemmaSummary">
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()
        return res_data

URL管理器url_manager.py


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
# -*- coding:utf-8 -*-
# url管理器


class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

    # 添加url
    def add_new_url(self, url):
        if url is None:
            return
        # 当url既不在新的列表中也不在旧的列表中时，则将其添加到新的url——set()集合中
        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)

    # 判断是否还有待爬取的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

定义路径输出结果


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35

# -*- coding:utf-8 -*-
# 最后的结果输出
# 提供两个功能，一个事收集数据，另一个是输出数据


class HtmlOutputer(object):
    # 收集数据需要一个列表list进行维护
    def __init__(self):
        self.datas= []

    def collect_data(self, data):
        if data is None:
            return
        self.datas.append(data)

    # 输出一个html文档
    def output_html(self):
        fileout = open("output.html", "w", encoding='utf-8')
        fileout.write("<html>")
        fileout.write("<head>")
        fileout.write("<meta charset=\'utf-8\'>")
        fileout.write("</head>")
        fileout.write("<body>")
        fileout.write("<table>")
        for data in self.datas:
            fileout.write("<tr>")
            fileout.write("<td>%s</td>" % data['url'])
            fileout.write("<td>%s</td>" % data['title'])
            fileout.write("<td>%s</td>" % data['summary'])
            fileout.write("</tr>")
        fileout.write("</table>")
        fileout.write("</body>")
        fileout.write("</html>")
        fileout.close()