import datetime import pathlib from urllib.parse import urljoin import pandas as pd import requests from bs4 import BeautifulSoup base_url = "http://www.qq.pref.ehime.jp/qq38/WP0805/RP080501BL" payload = { "_blockCd": "", "forward_next": "…

import datetime import os import re import time from urllib.parse import urljoin import requests import tweepy from bs4 import BeautifulSoup consumer_key = os.environ["CONSUMER_KEY"] consumer_secret = os.environ["CONSUMER_SECRET"] access_t…

import pathlib from urllib.parse import urljoin import pandas as pd import requests from bs4 import BeautifulSoup base_url = "http://www.qq.pref.ehime.jp/qq38/WP0805/RP080501BL" payload = { "_blockCd": "", "forward_next": "", "torinBlockDe…

import pandas as pd def str2time(s): df0 = s.str.extract("(翌日)?(\d{1,2}):(\d{1,2})").rename( columns={0: "day", 1: "hour", 2: "minute"} ) df0["day"] = df0["day"].map({"翌日": 1}) df1 = df0.fillna(0).astype(int) result = df1.apply( lambda…

# --- coding: utf-8 --- import datetime import re from urllib.parse import urljoin import requests import twitter from bs4 import BeautifulSoup def scraping(html): soup = BeautifulSoup(html, "html.parser") # スクレイピング tables = soup.fi…

今治地区の救急病院をスクレイピングし曜日別・医療機関別に集計する seleniumを使わずにrequestsでpost送信 Firefoxの開発ツールでpost内容を確認 ネットワークの中からメソッドPOSTを選びパラメーターのフォームデータを確認 "blockCd[3]": "", "forward_n…