phillipsm

import requests, time
from bs4 import BeautifulSoup

# We've now imported the two packages that will do the heavy lifting
# for us, reqeusts and BeautifulSoup

# This is the URL that lists the current inmates
# Should this URL go away, and archive is available at
# http://perma.cc/2HZR-N38X
url_to_scrape = 'http://apps2.polkcountyiowa.gov/inmatesontheweb/'

phillipsm

time.sleep(1)

phillipsm

$ python process.py 
CRAIG ELTON GILLEN, 20
White Male from SPRING HILL, IA
Booked at 7/6/2015 11:51 AM

JEREMY MONTEZ AMERISON SMITH, 27
Black Male from CLIVE, IA
Booked at 7/6/2015 11:45 AM

.

phillipsm

inmate_cities =  {}
 
for inmate in inmates:
    if inmate['city'] in inmate_cities:	
        inmate_cities[inmate['city']] += 1
    else:
        inmate_cities[inmate['city']] = 1
 
print inmate_cities

phillipsm

inmates = []
 
for inmate_link in inmates_links[:10]:
    r = requests.get(inmate_link)
    soup = BeautifulSoup(r.text)
	
    inmate_details = {}
	
    inmate_profile_rows = soup.select("#inmateProfile tr")
    inmate_details['age'] = inmate_profile_rows[0].findAll('td')[0].text.strip()

phillipsm

url_to_scrape = 'http://apps2.polkcountyiowa.gov/inmatesontheweb/'
 
r = requests.get(url_to_scrape)
 
soup = BeautifulSoup(r.text)
 
inmates_links = []
 
for table_row in soup.select(".inmatesList tr"):
	table_cells = table_row.findAll('td')

phillipsm

import requests
from bs4 import BeautifulSoup

phillipsm

import requests
from bs4 import BeautifulSoup
import time

# We've now imported the two packages that will do the heavy lifting
# for us, reqeusts and BeautifulSoup

# This is the URL that lists the current inmates
# Should this URL go away, and archive is available at
# http://perma.cc/2HZR-N38X

phillipsm

All material used for dgmde15

still dumping material in here

phillipsm

import requests
from bs4 import BeautifulSoup

# We've now imported the two packages that will do the heavy lifting
# for us, reqeusts and BeautifulSoup

# Let's put the URL of the page we want to scrape in a variable
# so that our code down below can be a little cleaner
url_to_scrape = 'http://apps2.polkcountyiowa.gov/inmatesontheweb/'