Python爬虫学习笔记

参照七月的原生爬虫教程练习结果，有部分修改

代码

from urllib import request
import re
import operator

class Spider(object):
    url = 'https://www.panda.tv/cate/lol'
    root_pattern = '
([\s\S]*?)
'
    name_pattern = '([\s\S]*?)'
    number_pattern = '([\s\S]*?)'

    def __fetch_content(self):
        r = request.urlopen(Spider.url)
        htmls = r.read()
        htmls = str(htmls, encoding='utf-8')
        return htmls

    def __analysis(self, htmls):
        root_html = re.findall(Spider.root_pattern, htmls)
        anchors = []
        for html in root_html:
            name = re.findall(Spider.name_pattern, html)[0].strip()
            number = re.findall(Spider.number_pattern, html)
            if '万' in number[0]:
                number = number[0].rstrip('万')
                number = float(number) * 10000
            else:
                number = float(number[0])
            anchor = {'name': name, 'number': number}
            anchors.append(anchor)
        return anchors

    def __sort(self, anchors):
        anchors = sorted(anchors, key = operator.itemgetter('number'), reverse = True)
        return anchors
    
    def __show(self, anchors):
        for ranking, anchor in enumerate(anchors, start = 1) :
            print(f"第{ranking}位, {anchor['name']} --- {int(anchor['number'])} ")

    def go(self):
        htmls = self.__fetch_content()
        anchors = self.__analysis(htmls)
        anchors = self.__sort(anchors)
        self.__show(anchors)

spider = Spider()
spider.go()