# -*- coding: utf-8 -*-

import urllib.request
from bs4 import BeautifulSoup

#Initialization of Contribution number
cont = []
for i in range(10):
    cont.append(0)
    
#Title initialization
title = []
for i in range(10):
    title.append("")

page_num = 1

while True:
    try:
        html = urllib.request.urlopen("https://qiita.com/tags/Python/items?page=" + str(page_num)).read()
        
        soup = BeautifulSoup(html, "html.parser")
        
        #HTML extraction by specifying the class
        title_all = soup.find_all(class_="publicItem_body")
        
        # publicItem_Skip pages without body class
        if len(title_all) == 0:
            continue
        
        for i in range(20):
            try:          
                #HTML extraction by specifying the class
                cont_all = soup.find_all(class_="publicItem_stockCount")
                #Remove annoying tags
                cont_sakujo = str(cont_all[i]).replace('<i class="fa fa-stock "></i>','')
                # cont_all_Since after is str type, string property cannot be used
                #Therefore, convert to Beautiful Soup type
                cont_kazu = int(BeautifulSoup(cont_sakujo, "html.parser").string)
                
                for j in range(10):
                    if cont_kazu >= cont[j]:
                        #Contribution number substitution
                        cont.insert(j, cont_kazu)
                        cont.pop()
                        #Title assignment
                        title.insert(j, title_all[i])
                        title.pop()
                        break
                
            #Skip articles that are not stocked by anyone
            except:
                continue
        
        page_num += 1
        
    # HTTP Error 404
    except:
        break

for i in range(len(title)):
    print (str(cont[i]) + "　" + str(title[i].a).replace('href="', 'href="http://qiita.com') + "<br>")

Recommended Posts