食べログの店舗情報をいい感じにScrapboxに登録するPythonistaスクリプト

tabelog-to-scrapbox.py

import appex
import re
import requests
import urllib
from objc_util import *
from bs4 import BeautifulSoup


def main():
    if not appex.is_running_extension():
        print('Running in Pythonista app, using test data...\n')
        url = 'https://tabelog.com/tokyo/A1302/A130201/13136102/'
    else:
        url = appex.get_url()
    if url:
        # TODO: Your own logic here...
        print('Input URL: %s' % (url, ))
        res = Restaurant.init_with_url(url)
        if res:
            print(res.name)
            print(res.location)
            print(res.category)
            print(res.image)

            baseURL = 'https://scrapbox.io/hem6-private/'
            title = urllib.parse.quote(res.name)
            raw_body = '[{}]\n[{} {}]\n#飲み屋 #{} #{}'.format(
                res.image, res.page_title, res.page_url, res.location,
                res.category)
            body = urllib.parse.quote(raw_body)

            scrapbox_url = baseURL + title + '?body=' + body
            app = UIApplication.sharedApplication()
            app.openURL_(nsurl(scrapbox_url))

        else:
            print('食べログのページじゃないかも')
    else:
        print('No input URL found.')


class Restaurant(object):
    def __init__(self, name, location, category, image, page_title, page_url):
        self.name = name
        self.location = location
        self.category = category
        self.image = image
        self.page_title = page_title
        self.page_url = page_url

    @classmethod
    def init_with_url(cls, url):
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html5lib')

        title = soup.title.string
        match = re.match(r'(.+) \- (.+)/(.+) \[食べログ\]', title)

        if not match:
            print('タイトルが食べログっぽくない: ', title)
            return None

        name = match.group(1)
        location = match.group(2)
        category = match.group(3)

        og_image = soup.find('meta', property='og:image')
        image = og_image['content'] if og_image else ''
        return Restaurant(name, location, category, image, title, url)


if __name__ == '__main__':
    main()