Python——爬取百度百科关键词1000个相关网页

最新推荐文章于 2022-04-30 20:15:19 发布

weixin_30919235

最新推荐文章于 2022-04-30 20:15:19 发布

阅读量556 爬虫 python 开发工具

原文链接：http://www.cnblogs.com/Jery-9527/p/10701113.html

Python简单爬虫——爬取百度百科关键词1000个相关网页——标题和简介

网站爬虫由浅入深：慢慢来

分析：

链接的URL分析：

数据格式：

爬虫基本架构模型：

本爬虫架构：

源代码：

# coding:utf8
# author:Jery
# datetime:2019/4/12 19:22
# software:PyCharm
# function:爬取百度百科关键词python1000个相关网页——标题和简介
from urllib.request import urlopen
import re
from bs4 import BeautifulSoup


class SpiderMain(object):
    def __init__(self):
        self.urls = UrlManager()
        self.downloader = HtmlDownloader()
        self.parser = HtmlParser()
        self.outputer = DataOutputer()

    # 主爬虫，调度四个类的方法执行爬虫
    def crawl(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("crawl 第{} ：{} ".format(count, new_url))
                html_content = self.downloader.download(new_url)
                new_urls, new_data = self.parser.parse(new_url, html_content)
                # 新网页的url及数据
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)
                if count == 1000:
                    break
                count += 1
            except:
                print(" crawl failed! ")
        self.outputer.output_html()

# URL管理器，实现URL的增加与删除
class UrlManager:
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

    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

    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.new_urls.add(url)

# 下载网页源代码
class HtmlDownloader:
    def download(self, url):
        if url in None:
            return
        response = urlopen(url)
        if response.getcode() != 200:
            return
        return response.read()

# 下载网页所需内容
class HtmlParser:
    def parse(self, page_url, html_content):
        if page_url is None or html_content is None:
            return
        soup = BeautifulSoup(html_content, 'lxml', 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/.*'))
        for link in links:
            new_url = "https://baike.baidu.com" + link['href']
            new_urls.add(new_url)
        return new_urls

    def _get_new_data(self, page_url, soup):
        res_data = {}
        # <dl class="lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-">
        # <dd class="lemmaWgt-lemmaTitle-title">
        # <h1>Python</h1>
        title_node = soup.find("dl", {"class": "lemmaWgt-lemmaTitle lemmaWgt-lemmaTitle-"}).dd.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

# 将所搜集数据输出至html的表格中
class DataOutputer:
    def __init__(self):
        self.datas = []

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

    def output_html(self):
        output = open('output.html', 'w')
        output.write("<html>")
        output.write("<body>")
        output.write("<table>")
        for data in self.datas:
            output.write("<tr>")
            output.write("<td>{}</td>".format(data['url']))
            output.write("<td>{}</td>".format(data['title'].encode('utf-8')))
            output.write("<td>{}</td>".format(data['summary'].encode('utf-8')))
            output.write("</tr>")
        output.write("</table>")
        output.write("<body>")
        output.write("</html>")
        output.close()


if __name__ == '__main__':
    root_url = "https://baike.baidu.com/item/Python/407313"
    obj_spider = SpiderMain()
    obj_spider.crawl(root_url)