Created
February 19, 2014 00:38
-
-
Save markuskreitzer/9083782 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import urllib2 | |
import urllib | |
from BeautifulSoup import BeautifulSoup, Comment | |
from pprint import pprint | |
url = 'http://www.alicehendersonrealty.com/ajax/' | |
query = { | |
'type_of_property': 'Rental', | |
'min_price': 0, | |
'max_price': 1500, | |
'number_of_bedrooms': 2, | |
'number_of_bathrooms': 1, | |
'property_city': 'Auburn', | |
'functionz': 'filter_form' | |
} | |
data = urllib.urlencode(query) | |
#print data | |
request = urllib2.Request(url) | |
request.add_header("Accept","Application/XML") | |
result = urllib2.urlopen(request,data) | |
t = result.read() | |
bs = BeautifulSoup(t) | |
results = [] | |
for row in bs.findAll('tr'): | |
#print row | |
results.append( { 'picture_link' : row.findChild().findChild()['src'], | |
'detail_link' : row.findAll('a')[0]['href'], | |
'pet_friendly': row.findAll('p')[1].string, | |
'address' : row.findAll('address')[0].string, | |
'is_available' : row.findAll('p')[0].string, | |
'rent_price' : row.findAll('h1')[0].getText() | |
} | |
) | |
#### END for | |
pprint(results,indent=4) | |
# Initial Idea came from: | |
"""curl 'http://www.alicehendersonrealty.com/ajax/' --data 'type_of_property=Rental+All&min_price=0&max_price=1500&number_of_bedrooms=2&number_of_bathrooms=1&property_city=Auburn&functionz=filter_form' | |
-H 'Cookie: __utma=266093791.1889026828.1392739854.1392739854.1392761320.2; __utmb=266093791.20.10.1392761320; __utmc=266093791; __utmz=266093791.1392761320.2.2.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=http%3A%2F%2Fwww.alicehendersonrealty.com%2Frental%2F928-e-glenn%2F' | |
-H 'Origin: http://www.alicehendersonrealty.com' | |
-H 'Accept-Encoding: gzip,deflate,sdch' | |
-H 'Accept-Language: en-US,en;q=0.8,af;q=0.6' | |
-H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1700.107 Safari/537.36' | |
-H 'Content-Type: application/x-www-form-urlencoded' | |
-H 'Accept: text/html, */*; q=0.01' | |
-H 'Referer: http://www.alicehendersonrealty.com/rentals/' | |
-H 'X-Requested-With: XMLHttpRequest' | |
-H 'Connection: keep-alive' | |
--compressed""" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment