Beautifulsoupの場合
import csv
from bs4 import BeautifulSoup
import requests
url = 'http://www.example.com/'
r = requests.get(url)
if r.status_code == requests.codes.ok:
soup = BeautifulSoup(r.content, 'html.parser')
result = [[[td.get_text(strip=True) for td in trs.select('th, td')]
for trs in table.select('tr')]
for table in soup.select('table')]
print(len(result))
print(result)
with open('result.csv', 'w') as fw:
writer = csv.writer(fw, dialect='excel', lineterminator='\n')
writer.writerows(result[0])
Pandasの場合
import pandas as pd
url = 'http://www.example.com/'
dfs = pd.read_html(url, header=0, index_col=0)
print(len(dfs))
print(dfs)
dfs[0].to_csv('result.csv')