Pythonで歴代総長をWebスクレイピング #code

webscraper.py

import requests
from bs4 import BeautifulSoup
import csv


if __name__ == '__main__':
    csvFile = open("ut_soutyou.csv", 'w', encoding='utf-8_sig', newline='')
    writer = csv.writer(csvFile)
    target_url = "http://www.u-tokyo.ac.jp/gen01/b01_03_j.html"
    # target_url = "http://www.ynu.ac.jp/about/president/successive.html"
    # Requestsを使って、webから取得
    r = requests.get(target_url)
    # 要素を抽出
    soup = BeautifulSoup(r.content, 'lxml')
    table = soup.findAll("table")[0]
    elems = table.findAll("tr")
    for e in elems:
        csvRow = []
        if len(e.findAll(['td', 'th'])) is 4:
            csvRow.append(' ')
        for cell in e.findAll(['td', 'th']):
            print(cell.get_text())
            csvRow.append(cell.get_text())
        writer.writerow(csvRow)
    csvFile.close()