gistfile1.py

from __future__ import print_function
from lxml.html.soupparser import fromstring
import requests
from datetime import datetime, timedelta


start_date = datetime(2012, 8, 6)
end_date = start_date + timedelta(days=45)

url = 'http://www.reserveamerica.com/campsiteCalendar.do?page=calendar&contractCode=CA&parkId=120030&calarvdate={caldate}&sitepage=true&startIdx={page_index}&sitefilter=STANDARD'
s = requests.session()
s.config['keep_alive'] = False
calendar_start = start_date
calendar_page = 1
page_downloaded = 1
while calendar_start < end_date:
    days = []
    for i in range(14):
        days.append(calendar_start + timedelta(days=i))
    calendar_start_str = calendar_start.strftime("%m/%d/%Y")
    page_index = 0
    while page_index < 125:
        page_url = url.format(caldate=calendar_start_str,
                page_index=page_index)
        print(page_url)
        page_request = requests.get(page_url, prefetch=True)
        page = page_request.content
        with open ("page{}.html".format(page_downloaded), 'w') as f:
            f.write(page)
        page_downloaded += 1
        tree = fromstring(page)
        sites = []
        # availability = defaultdict(set)
        availables = []
        availables = tree.cssselect('td.status.a')
        # print(len(availables))

        for item in availables:
            row = item.getparent()
            site_id = row[0].text_content().split('\n')[0]
            if site_id not in sites:
                sites.append(site_id)
                for i, cell in enumerate(row[2:]):
                    if cell not in availables:
                        continue
                    cell_date = days[i]
                    if cell_date.weekday() in [4, 5]:
                        print("booya -- site: {} on {}".format(site_id, cell_date))
        page_index += 25
    calendar_start = calendar_start + timedelta(days=14)