Python3_第一个简单爬虫开发_爬取百度百科1000个词条_参照慕课网教程实现

参照慕课网教程，写了第一个爬虫------爬取百度百科“python”词条相关页面一千个。

该爬虫会在“python”页面中发现其他链接并自动继续爬取。原课程是用python2.7 写的，我改用了python3.6.

部分模块的位置有变化，需要注意。

第一个文件:

spider_main.py

import html_downloader import html_outputer import html_parser import url_manager

class SpiderMain(object):     def __init__(self):         # 创建所需要的URL管理器对象         # 下载器对象,分析器对象,html输出对象         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):         """         爬虫逻辑实现的主方法,输入跟网页即可爬1000个网页

        :param root_url: 输入要爬取的根网页         """         count = 1         # 先把根目录添加到url管理器中         self.urls.add_new_url(root_url)         # 当管理器中有url时一直爬取         while self.urls.has_new_url():             # 避免爬取出错的异常,部分网站无法打开会引发异常             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 += 1

            except:                 print('craw failed')

        self.outputer.output_html()

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

第二个文件

html_downloader.py

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()

第三个文件：

使用了bs4中的BeautifulSoup 模块和正则表达式来分析网页内容获得指定信息

import html_parser.py

 

from bs4 import BeautifulSoup
import re
import urllib.parse
class HtmlParser(object):

    def _get_new_urls(self, page_url, soup):
        # /item/12345
        new_urls = set()
        links = soup.find_all('a', href=re.compile(r"^/item/*"))
        for link in links:
            new_url = link ['href']
            new_full_url = urllib.parse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        return new_urls

    def _get_new_data(self, page_url, soup):
        res_data = {}

        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()

        #<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

    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

 

 

 

 

第四个文件：

文件提供了可以管理url的方法，防止重复抓取和循环抓取

import url_manager.py

 

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 get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url


    def has_new_url(self):
        return len(self.new_urls) != 0

 

最后一个文件：

做了小改进，在html开始阶段加上 fout.write("<meta charset=\"UTF-8\">")

确保浏览器用UTF8编码格式打开。

import html_outputer.py

 

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("<meta charset=\"UTF-8\">")
        fout.write("<body>")
        fout.write("<table border=\"8\">")
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>" % data['url'])
            fout.write("<td>%s</td>" % data['title'])
            fout.write("<td>%s</td>" % data['summary'])
            fout.write("</tr>")
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")