第一个爬虫（爬文字）

最新推荐文章于 2024-08-03 19:27:22 发布

华仔哦

最新推荐文章于 2024-08-03 19:27:22 发布

阅读量189

点赞数 1

分类专栏：爬虫 python 文章标签：爬虫 python

本文链接：https://blog.csdn.net/laf_huazai/article/details/100903047

版权

爬虫同时被 2 个专栏收录

1 篇文章 0 订阅

订阅专栏

python

1 篇文章 0 订阅

订阅专栏

spider_main.py

from spider 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):
        self.urls.add_new_url(root_url)
        count = 1
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print("craw %d : %s"%(count, new_url))
                html_doc = self.downloader.download(new_url)
                html_data, html_url = self.parser.parse(new_url, html_doc)
                self.urls.add_new_url(html_url)
                self.outputer.collect_data(html_data)
                count = count+1
            except:
                print("craw failed")
            self.outputer.output_data()


if __name__ == "__main__":
    root_url = "http://www.wmtxt.net/book/5446/4217938.html"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

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

    def get_new_url(self):
        if self.new_urls is None:
            return
        else:
            return self.new_urls.pop()

    def add_new_urls(self, html_urls):
        if html_urls is None or len(html_urls) == 0:
            return
        for url in html_urls:
            self.new_urls.add(url)

html_downloader.py

import urllib.request
    class HtmlDownloader(object):
        def download(self, new_url):
            return urllib.request.urlopen(new_url).read()

html_parser.py

from urllib.parse import urljoin
from bs4 import BeautifulSoup

class HtmlParser(object):
    def parse(self, page_url, html_doc):

        if page_url is None or html_doc is None:
            return
        soup = BeautifulSoup(html_doc, 'html.parser', from_encoding='utf-8')

        new_url = self.get_new_url(page_url, soup)

        new_data = self.get_new_data(soup)

        return new_data, new_url

    @staticmethod
    def get_new_url(page_url, soup):
        new_url = soup.find('a', id="linkNext")['href']
        new_full_url = urljoin(page_url, new_url)
        return new_full_url

    @staticmethod
    def get_new_data(soup):
        res_data = ""
        datas = soup.find_all('br')
        for data in datas:
            res_data = res_data + data.get_text()
        return res_data

html_outputer.py

class HtmlOutputer(object):
    def __init__(self):
        self.datas = []

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

    def output_data(self):
        fout = open('output.html', 'w')
        fout.write("<html>")

        fout.write("<body>")
        for data in self.datas:
            fout.write("%s" % data)
        fout.write("<body>")

        fout.write("</html>")
        fout.close()

模仿自@慕课网@蚂蚁学

华仔哦

关注

1
点赞
踩
1

收藏

觉得还不错? 一键收藏
打赏
0
评论
第一个爬虫（爬文字）

spider_main.pyfrom spider import url_manager, html_downloader, html_parser, html_outputerclass SpiderMain(object): def __init__(self): self.urls = url_manager.UrlManager() self....
复制链接

扫一扫