日刊スポーツのサイトをスクレイプしてマー君の次回登板日をSlackに通知するスクリプト on ScrapingWiki

cron.python

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import scraperwiki
import requests
import re
from pyquery import PyQuery as pq

# 3rd party library
try:
    from urllib.parse import urljoin
    from urllib.parse import urlencode
    import urllib.request as urlrequest
except ImportError:
    from urlparse import urljoin
    from urllib import urlencode
    import urllib2 as urlrequest
import json


class Slack():

    def __init__(self, url=""):
        self.url = url
        self.opener = urlrequest.build_opener(urlrequest.HTTPHandler())

    def notify(self, **kwargs):
        """
        Send message to slack API
        """
        return self.send(kwargs)

    def send(self, payload):
        """
        Send payload to slack API
        """
        payload_json = json.dumps(payload)
        data = urlencode({"payload": payload_json})
        req = urlrequest.Request(self.url)
        response = self.opener.open(req, data.encode('utf-8')).read()
        return response.decode('utf-8')
try:
    pre_text = scraperwiki.sqlite.select("text from swdata where id=0 limit 1")[0]['text']
except:
    pre_text = ''
    pass
html = requests.get("http://www.nikkansports.com/baseball/mlb/japanese/masahiro-tanaka/news/")
d = pq(html.content)
for i in d('.newslist li a').items():
    pattern = ur"次"
    matchOB = re.search(pattern , i.text())
    
    if matchOB and pre_text != i.text():
        print '---------Send Slack----------'
        # Saving data:
        unique_keys = [ 'id' ]
        data = { 'id':0, 'text': i.text()}
        scraperwiki.sql.save(unique_keys, data)
        
        slack = Slack(url = "ここに投稿したいチャンネルのWeb hook URL")
        slack.notify(text = i.text())
        break
    elif matchOB and pre_text == i.text():
        break