Hsda.py

Hsda.py

# coding: utf-8
import os
import requests
import re
import json

# hdsa
if not os.path.exists('hdsa.html'):
    req =requests.request('get','http://hdsa.org/about-hdsa/locate-resources/')
    f = open('hdsa.html','w')
    f.write(req.content)
    f.close()

f = open('hdsa.html','r')
contents = f.read()
f.close()

match = re.search('\<script\> var allmarkers = (.*?)\<\/script>', contents)
data = json.loads(match.group(1))

fields = ['hdsatitle', 'hdsaname', 'address', 'suitefloor', 'citystate', 'zip', 'cliniccoordinator', 'affiliation', 'hdsatype', 'hdsaphone', 'hdsaemail', 'website', 'hdsaid']

with open('hdsa.csv','w') as f:
    f.write("'"+"','".join(list(s for s in fields))+"'\n")

    for record in data:
        opts = record['options']
        f.write("'"+"','".join((opts['hdsatitle'], opts['hdsaname'], opts['address'], opts['suitefloor'], opts['citystate'], opts['zip'], opts['cliniccoordinator'], opts['affiliation'], opts['hdsatype'], opts['hdsaphone'], opts['hdsaemail'], opts['website'], str(opts['hdsaid'])))+"'\n")

# hsa
if not os.path.exists('hsa.html'):
    req = requests.request('get','http://hda.org.uk/international.js')
    with open('hsa.html','w') as f:
        f.write(req.content)

with open('hsa.html','r') as f:
    contents = f.read()
        
match = re.search('IHA_Listing_Items = ([\S\s]*?);\n', contents)

data = json.loads(match.group(1).replace("'",'"').replace(',\n    }','\n    }').replace('\&','&'))
with open('hsa.csv','w') as f:
    f.write("'region','info','email','phone','website'\n")
    for record in data:
        region = record['Region']
        for contact in record['DetailsPlain'].split('\n\n'):
            emails = []
            numbers = []
            details = []
            websites = []
            contact = contact.strip()
            for line in contact.split('\n'):
                if '@' in line:
                    emails += [s.strip() for s in re.split(':|;|/',line)]
                elif 'Tel' in line or 'tel' in line or 'Fax' in line or 'Mobil' in line or 'Hotline' in line or 'Cellphone' in line:
                    numbers += [s.strip() for s in re.split(':|;',line)]
                elif 'Website' in line or 'www' in line or 'Facebook' in line or 'Twitter' in line:
                    websites += [s.strip() for s in re.split(':|;',line)]
                else:
                    details += [line]
            f.write("'"+"','".join((region, ';'.join(details), ';'.join(emails), ';'.join(numbers), ';'.join(websites)))+"'\n")
print('done')