A very fast web scraping script to get a CSV with Volxkino events. Importable to Google calendar

parse_volxkino.py

"""A very fast web scraping script to get a CSV with Volxkino events.
Importable to Google calendar.

Script written 2015.

[email protected]

Reuqirments:
 - BetautifulSoup 4: https://pypi.python.org/pypi/beautifulsoup4

"""

import csv
import codecs
import cStringIO
import itertools
import locale
from datetime import datetime
from bs4 import BeautifulSoup
import requests


URL = "http://volxkino.at/events/bevorstehend/page/{}/"

start_date = []
start_time = []
location = []
title = []
link = []
description = []


class CsvUnicodeWriter(object):
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """
    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)


# for date parsing...
locale.setlocale(locale.LC_TIME, ("de_AT.UTF-8", "de_AT.UTF-8"))

for page_num in itertools.count(start=1):

    page = requests.get(URL.format(page_num))
    soup = BeautifulSoup(page.text)
    if not soup.select('div.tribe-events-event'):
        print "page {} empty".format(page_num)
        break

    for event in soup.select('div.tribe-events-event'):
        start_datetime = event.select(
            '.tribe-events-event-list-meta td')[1].get_text().strip()

        dt = " ".join(start_datetime.split()[:-1])
        start_date.append(datetime.strptime(dt, "%d. %B %Y"
                                            ).strftime("%Y-%m-%d"))

        start_time.append(" ".join(start_datetime.split()[-1:]))
        title.append(event.select('h2.entry-title')[0].get_text())
        location.append(event.select(
            '.tribe-events-event-list-meta td')[-1].get_text().strip())

        # no link field for google calendar, prepend to description
        link = event.select('h2.entry-title a')[0].attrs['href']
        desc = event.select('div.entry-content')[0].get_text()
        description.append("%s\n\n%s" % (link, desc))


# possible fields:
# Subject, Start Date, Start Time, End Date, End Time, All Day Event,
# Reminder On/Off, Reminder Date, Reminder Time, Meeting Organizer,
# Description, Location, Private
csv_file = open("volxkino_calendar.csv", "w")
csv_writer = CsvUnicodeWriter(csv_file, quotechar='"', delimiter=',',
                              quoting=csv.QUOTE_ALL)
csv_writer.writerow(["Start Date", "Start Time", "Subject", "Location",
                     "Description"])
csv_writer.writerows(zip(start_date, start_time, title, location, description))