python程序导入import、规范化和封装自己写的.py文件

目录

1. 简单地导入自己写的.py文件

2. 将自己写的多个.py文件规范化成外部类，并创建__init__.py

 3. 将自己的程序封装成外部包

---

1. 简单地导入自己写的.py文件

将a.py与b.py放在同一项目路径下，然后在另一个b.py文件中执行import a.py，然后我们就可以在b.py中调用a.py中的函数了

import a

a.py()

参考：https://jingyan.baidu.com/article/08b6a591810daf14a8092204.html

2. 将自己写的多个.py文件规范化成外部类，并创建__init__.py

参考：https://github.com/fifths/python_baike_spider/tree/master/baike_spider

• 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()

• html_parser.py 

from bs4 import BeautifulSoup
import re
import urllib.parse


class HtmlParser(object):
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
        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 = {}

        # url
        res_data['url'] = page_url

        title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find('h1')
        res_data['title'] = title_node.get_text()

        # lemma-summary
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()

        return res_data

    def paser(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

• spider_main.py

from baike_spider import url_manager
from baike_spider import html_downloader
from baike_spider import html_parser
from baike_spider import 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.paser(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 = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

 3. 将自己的程序封装成外部包

参考：http://www.zzvips.com/article/84558.html; https://www.cnblogs.com/smileyes/p/7657591.html; https://www.cnblogs.com/mangM/p/11619247.html