一个简单的爬虫流程及实现

爬虫在数据采集方面有很多不错的应用，互联网就是数据的海洋，掌握好这一工具对与获得更多更宏观的数据有很大的意义。

一个简单的爬虫包括五个主要的部分

1 spider_main  一个调度的逻辑

2 url_manager url的管理器，复杂url的获得和去重 ，这一部分深度的可以利用redis的队列，以及深度广度优先原则

3 html_parser  html的解析器，获得html中想得到的数据和子url

4 html_downloader  具体执行下载逻辑的部分，深度的话会涉及cookid的处理，https，header，多线程，定时，反爬虫的策略

5 html_outputer  与数据库连接以及在前台的展现

分别的代码实现

1

from spider1 import url_manager, html_downloader, html_parser, html_outputer


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 == 10:
                    break
                count = count + 1
            except:
                print('craw failed')
        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/Python/407313"
    spider = SpiderMain()
    spider.craw(root_url)

2 

class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    def add_new_url(self, root_url):
        if root_url is None:
            return
        if root_url  not in self.new_urls and root_url  not in self.old_urls:
            self.new_urls.add(root_url)
    def add_new_urls(self, new_urls):
        if new_urls is None or len(new_urls) == 0:
            return
        for url in new_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

3 

import re
import urllib.parse
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
    # <a target="_blank" href="/item/%E6%BA%90%E4%BB%A3%E7%A0%81/3969" data-lemmaid="3969">源代码</a>
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        url_nodes = soup.find_all('a',href=re.compile(r"/item/*"))
        new_full_url = ''
        for url_node in url_nodes:
            if url_node.has_attr('data-lemmaid'):
                new_full_url = r"https://baike.baidu.com"+ url_node['href'] +r"/"+url_node['data-lemmaid']
                new_urls.add(new_full_url)
            else:
                new_full_url = r"https://baike.baidu.com"+ url_node['href']
                new_urls.add(new_full_url)

        return new_urls
    def _get_new_data(self,page_url,soup):
        title_content = {}
        title_node = soup.find('dd', class_='lemmaWgt-lemmaTitle-title').find('h1')
        title = title_node.get_text()
        content_nodes = soup.find_all('div',class_ = 'para')
        content = []
        for content_node in content_nodes:
            content.append(content_node.get_text())
        content_string = ''.join(content)
        title_content['title'] = title
        title_content['content'] = content_string
        # return  title_content
        return content_string

4

import urllib.request
class HtmlDownLoader(object):

    def download(self, url):
        if url is None:
            return None

        response = urllib.request.urlopen(url.encode('utf-8').decode('utf-8'))
        # if response.read().getcode() != 200:
        #     return None
        return response.read()

5

class HtmlOutputer(object):
    def collect_data(self, new_data):
        pass

    def output_html(self):
        pass

运行后的结果：