From c3a4ba319b7b9d617b820d84670159580ffae628 Mon Sep 17 00:00:00 2001
From: blablupcom <o.volodin@yahoo.com>
Date: Sat, 16 Jan 2016 23:09:27 +0300
Subject: [PATCH] First commit

---
 requirements.txt |   5 ++
 scraper.py       | 142 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 147 insertions(+)
 create mode 100644 requirements.txt
 create mode 100644 scraper.py

diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..690a611
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,5 @@
+-e git+http://github.com/openaustralia/scraperwiki-python.git@morph_defaults#egg=scraperwiki
+lxml==3.4.4
+cssselect==0.9.1
+beautifulsoup4
+
diff --git a/scraper.py b/scraper.py
new file mode 100644
index 0000000..387bb6d
--- /dev/null
+++ b/scraper.py
@@ -0,0 +1,142 @@
+# -*- coding: utf-8 -*-
+
+#### IMPORTS 1.0
+
+import os
+import re
+import scraperwiki
+import urllib2
+from datetime import datetime
+from bs4 import BeautifulSoup
+
+#### FUNCTIONS 1.2
+import requests       # import requests for validating urls
+
+def validateFilename(filename):
+    filenameregex = '^[a-zA-Z0-9]+_[a-zA-Z0-9]+_[a-zA-Z0-9]+_[0-9][0-9][0-9][0-9]_[0-9QY][0-9]$'
+    dateregex = '[0-9][0-9][0-9][0-9]_[0-9QY][0-9]'
+    validName = (re.search(filenameregex, filename) != None)
+    found = re.search(dateregex, filename)
+    if not found:
+        return False
+    date = found.group(0)
+    now = datetime.now()
+    year, month = date[:4], date[5:7]
+    validYear = (2000 <= int(year) <= now.year)
+    if 'Q' in date:
+        validMonth = (month in ['Q0', 'Q1', 'Q2', 'Q3', 'Q4'])
+    elif 'Y' in date:
+        validMonth = (month in ['Y1'])
+    else:
+        try:
+            validMonth = datetime.strptime(date, "%Y_%m") < now
+        except:
+            return False
+    if all([validName, validYear, validMonth]):
+        return True
+
+
+def validateURL(url):
+    try:
+        r = requests.get(url, allow_redirects=True, timeout=20)
+        count = 1
+        while r.status_code == 500 and count < 4:
+            print ("Attempt {0} - Status code: {1}. Retrying.".format(count, r.status_code))
+            count += 1
+            r = requests.get(url, allow_redirects=True, timeout=20)
+        sourceFilename = r.headers.get('Content-Disposition')
+        if sourceFilename:
+            ext = os.path.splitext(sourceFilename)[1].replace('"', '').replace(';', '').replace(' ', '')
+        else:
+            ext = os.path.splitext(url)[1]
+        validURL = r.status_code == 200
+        validFiletype = ext.lower() in ['.csv', '.xls', '.xlsx', '.pdf']
+        return validURL, validFiletype
+    except:
+        print ("Error validating URL.")
+        return False, False
+
+
+
+def validate(filename, file_url):
+    validFilename = validateFilename(filename)
+    validURL, validFiletype = validateURL(file_url)
+    if not validFilename:
+        print filename, "*Error: Invalid filename*"
+        print file_url
+        return False
+    if not validURL:
+        print filename, "*Error: Invalid URL*"
+        print file_url
+        return False
+    if not validFiletype:
+        print filename, "*Error: Invalid filetype*"
+        print file_url
+        return False
+    return True
+
+
+def convert_mth_strings ( mth_string ):
+    month_numbers = {'JAN': '01', 'FEB': '02', 'MAR':'03', 'APR':'04', 'MAY':'05', 'JUN':'06', 'JUL':'07', 'AUG':'08', 'SEP':'09','OCT':'10','NOV':'11','DEC':'12' }
+    for k, v in month_numbers.items():
+        mth_string = mth_string.replace(k, v)
+    return mth_string
+
+#### VARIABLES 1.0
+
+entity_id = "NFTRTP_SASHNFT_gov"
+url = "http://www.surreyandsussex.nhs.uk/about-us/freedom-of-information/list-and-registers/publication-of-spend-over-25000-pounds/"
+errors = 0
+data = []
+
+#### READ HTML 1.2
+
+html = requests.get(url)
+soup = BeautifulSoup(html.text, 'lxml')
+
+
+#### SCRAPE DATA
+
+blocks = soup.find_all('div', 'accordion-content')
+for block in blocks:
+    links = block.find_all('a')
+    for link in links:
+        try:
+            if '.csv' in link['href'] or '.xls' in link['href'] or '.xlsx' in link['href'] or '.pdf' in link['href']:
+
+                url = link['href']
+                title = link.text.strip().split('GL Expenditure')[-1].split(u'–')[-1].strip()
+                csvMth = title[:3]
+                csvYr = title[-4:]
+                if 'r 15' in csvYr:
+                    csvYr = '2015'
+                csvMth = convert_mth_strings(csvMth.upper())
+                data.append([csvYr, csvMth, url])
+        except:
+            pass
+
+
+
+
+
+#### STORE DATA 1.0
+
+for row in data:
+    csvYr, csvMth, url = row
+    filename = entity_id + "_" + csvYr + "_" + csvMth
+    todays_date = str(datetime.now())
+    file_url = url.strip()
+
+    valid = validate(filename, file_url)
+
+    if valid == True:
+        scraperwiki.sqlite.save(unique_keys=['l'], data={"l": file_url, "f": filename, "d": todays_date })
+        print filename
+    else:
+        errors += 1
+
+if errors > 0:
+    raise Exception("%d errors occurred during scrape." % errors)
+
+
+#### EOF