PyCon US Parser

parse_pycon_us.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# requirements: opterator, requests
import csv
import requests
from lxml import html
from opterator import opterate


def get_tree():
    text = requests.get('https://us.pycon.org/2012/schedule/').text
    tree = html.fromstring(text)
    return tree


def parse_tree(tree):
    presentations = tree.xpath('//td[contains(@class, "presentation")]')
    for pr in presentations:
        title = pr.xpath('div[@class="title"]/a/text()')[0]
        url = 'https://us.pycon.org' + pr.xpath('div[@class="title"]/a/@href')[0]
        speaker = pr.xpath('div[@class="speaker"]/text()')[0]
        yield (title, url, speaker)


def write_csv(filename, records):
    with open(filename, 'w') as fd:
        writer = csv.writer(fd)
        for row in records:
            row = [i.encode('utf-8') for i in row]
            writer.writerow(row)

@opterate
def main(filename):
    tree = get_tree()
    records = parse_tree(tree)
    write_csv(filename, records)

main()