import requests
from bs4 import BeautifulSoup

def main():
    writers = dict()

    for i in range(1,600):
        #Announcement is https://atcoder.jp/posts/+Number format
        #It is necessary to change 600 in the range of the for statement as appropriate and execute it (because I do not know how many notifications there are)
        load_url = "https://atcoder.jp/posts/" + str(i)
        html = requests.get(load_url)
        soup = BeautifulSoup(html.content, "html.parser")
        title = soup.title.text

        #Process only when the contest is announced
        if title.find("Announcement") >=0 :
            contestName = title[0:title.find("Announcement")-1]

            #Since the writer name etc. are escaped, parse the html part in the text again
            soup2 = BeautifulSoup(soup.text,"html.parser")
            username_elements = soup2.find_all('a', class_='username')
            if len(username_elements) > 0:
                for item in username_elements:
                    #item.The writer name is stored in text
                    if item.text in writers:
                        writers[item.text].append(contestName)
                    else:
                        writers[item.text] = [contestName]
    #output
    for writer in writers:
        print(writer, writers[writer])

if __name__ == '__main__':
    main()

Recommended Posts