From 5ba4a625c769fbe4d1e3541bb14e23347c1c7dfe Mon Sep 17 00:00:00 2001
From: "duncan.parkes" <duncan.parkes@cf68f80a-222c-0410-aabe-5f79d0504a29>
Date: Sun, 21 Oct 2007 21:53:45 +0000
Subject: [PATCH] Add back in the Enfield scraper which I probably deleted
 automatically a while back. Sorry!

---
 python_scrapers/Enfield.cgi          | 121 +++++++++++++++++++++++++++
 python_scrapers/OtherFilesToCopy.csv |   1 +
 2 files changed, 122 insertions(+)
 create mode 100644 python_scrapers/Enfield.cgi

diff --git a/python_scrapers/Enfield.cgi b/python_scrapers/Enfield.cgi
new file mode 100644
index 0000000..7462ebd
--- /dev/null
+++ b/python_scrapers/Enfield.cgi
@@ -0,0 +1,121 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+
+use CGI qw(:cgi);
+use HTML::TreeBuilder;
+use LWP::UserAgent;
+use XML::Writer;
+
+
+# The master URLs for the Enfield planning search
+our $SearchURL = "http://forms.enfield.gov.uk/swiftlg/apas/run/WPHAPPCRITERIA";
+our $InfoURL = "http://forms.enfield.gov.uk/swiftlg/apas/run/WPHAPPDETAIL.DisplayUrl?theApnID=";
+
+# We're a CGI script...
+my $query = CGI->new();
+
+# Get the date to fetch
+my $date = $query->param("day") . "/" . $query->param("month") . "/" . $query->param("year");
+
+# Construct an LWP user agent
+our $UA = LWP::UserAgent->new(env_proxy => 1);
+
+# Do the search
+my $page = do_post($SearchURL,
+                   {"REGFROMDATE.MAINBODY.WPACIS.1." => $date,
+                    "REGTODATE.MAINBODY.WPACIS.1." => $date,
+                    "SEARCHBUTTON.MAINBODY.WPACIS.1." => "Search"});
+
+# Output an HTTP response header
+print $query->header(-type  => "text/xml");
+
+# Create an XML output stream
+my $Writer = XML::Writer->new(DATA_MODE => 1);
+
+# Output the XML header data
+$Writer->xmlDecl("UTF-8");
+$Writer->startTag("planning");
+$Writer->dataElement("authority_name", "Enfield Council");
+$Writer->dataElement("authority_short_name", "Enfield");
+$Writer->startTag("applications");
+
+# Output any applications on the first page
+output_applications($page);
+
+# Loop over any additional results pages
+foreach my $link ($page->look_down("_tag" => "a", "href" => qr/^WPHAPPSEARCHRES\.displayResultsURL/))
+{
+    # Fetch this page...
+    $page = do_get(URI->new_abs($link->attr("href"), $SearchURL));
+
+    # ...and output the applications from it
+    output_applications($page);
+}
+
+# Finish off XML output
+$Writer->endTag("applications");
+$Writer->endTag("planning");
+$Writer->end();
+
+exit 0;
+
+# Make a GET request
+sub do_get
+{
+    my $response = $UA->get(@_);
+
+    die $response->status_line unless $response->is_success;
+
+    return HTML::TreeBuilder->new_from_content($response->content);
+}
+
+# Make a POST request
+sub do_post
+{
+    my $response = $UA->post(@_);
+
+    die $response->status_line unless $response->is_success;
+
+    return HTML::TreeBuilder->new_from_content($response->content);
+}
+
+# Output applications from a results page
+sub output_applications
+{
+    my $page = shift;
+
+    # Find the result table
+    my $table = $page->look_down("_tag" => "table", "class" => "apas_tbl");
+
+    # Process each row of the results
+    foreach my $row ($table->look_down("_tag" => "tr"))
+    {
+        my @cells = $row->look_down("_tag" => "td");
+
+        if (@cells >= 3)
+        {
+            my $reference = $cells[0]->as_trimmed_text;
+            my $description = $cells[1]->as_trimmed_text;
+            my $address = $cells[2]->as_trimmed_text;
+            my $postcode;
+
+            if ($address =~ /\s+([A-Z]+\d+\s+\d+[A-Z]+)$/)
+            {
+                $postcode = $1;
+            }
+
+            $Writer->startTag("application");
+            $Writer->dataElement("council_reference", $reference);
+            $Writer->dataElement("address", $address);
+            $Writer->dataElement("postcode", $postcode);
+            $Writer->dataElement("description", $description);
+            $Writer->dataElement("info_url", $InfoURL . $reference);
+            $Writer->dataElement("date_received", $date);
+            $Writer->endTag("application");
+        }
+    }
+
+    return;
+}
diff --git a/python_scrapers/OtherFilesToCopy.csv b/python_scrapers/OtherFilesToCopy.csv
index 91714e7..5457d3c 100644
--- a/python_scrapers/OtherFilesToCopy.csv
+++ b/python_scrapers/OtherFilesToCopy.csv
@@ -10,3 +10,4 @@
 "Broxbourne.cgi", "493"
 "EastHerts.cgi", "493"
 "NorthHerts.cgi", "493"
+"Enfield.cgi", "493"
\ No newline at end of file