From 99924285c510ac8f4ba8042dd3fa701e7017f56c Mon Sep 17 00:00:00 2001
From: Nemo <me@captnemo.in>
Date: Tue, 2 Jan 2018 00:19:07 +0530
Subject: [PATCH] Initial commit

---
 .gitignore   |  2 ++
 Gemfile      |  4 ++++
 Gemfile.lock | 19 +++++++++++++++++++
 README.md    | 14 ++++++++++++++
 bootstrap.sh | 20 ++++++++++++++++++++
 parse_dir.rb | 11 +++++++++++
 6 files changed, 70 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Gemfile
 create mode 100644 Gemfile.lock
 create mode 100644 README.md
 create mode 100755 bootstrap.sh
 create mode 100644 parse_dir.rb

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..681c030
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+vendor/
+html/
\ No newline at end of file
diff --git a/Gemfile b/Gemfile
new file mode 100644
index 0000000..0e95724
--- /dev/null
+++ b/Gemfile
@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+gem 'net-http2'
+gem 'nokogiri'
\ No newline at end of file
diff --git a/Gemfile.lock b/Gemfile.lock
new file mode 100644
index 0000000..5f3225d
--- /dev/null
+++ b/Gemfile.lock
@@ -0,0 +1,19 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    http-2 (0.8.4)
+    mini_portile2 (2.3.0)
+    net-http2 (0.16.0)
+      http-2 (= 0.8.4)
+    nokogiri (1.8.1)
+      mini_portile2 (~> 2.3.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  net-http2
+  nokogiri
+
+BUNDLED WITH
+   1.16.1
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..e9b243e
--- /dev/null
+++ b/README.md
@@ -0,0 +1,14 @@
+# bengaluru-food-census
+
+Keep track of restaurant openings and closures in the city.
+
+# Quirk
+
+Zomato does not support HTTP/1.1, so wget can't be used.
+
+
+# Features
+
+- Keep track of historical data
+- Does not use the API (since the rate-limit is too low at 1k/day)
+    + We need to checkou around 8k restaurant status
\ No newline at end of file
diff --git a/bootstrap.sh b/bootstrap.sh
new file mode 100755
index 0000000..af1da0e
--- /dev/null
+++ b/bootstrap.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+ZOMATO_ROOT_URL=https://www.zomato.com
+ZOMATO_CITY=bangalore
+DIRECTORY_URL="$ZOMATO_ROOT_URL/$ZOMATO_CITY/directory"
+USER_AGENT="Mozilla/Gecko/Firefox/58.0"
+
+mkdir -p html
+
+function dl() {
+    echo "[+] $2"
+    curl -sS --http2-prior-knowledge --compressed -H "User-Agent: $USER_AGENT" $1 > "html/$2"
+}
+
+dl "$DIRECTORY_URL" "directory.html"
+
+while read -r LINK; do
+    FILENAME="$(basename $LINK).html"
+    dl "$LINK" "$FILENAME"
+done <<< $(bundle exec ruby parse_dir.rb)
diff --git a/parse_dir.rb b/parse_dir.rb
new file mode 100644
index 0000000..38838d2
--- /dev/null
+++ b/parse_dir.rb
@@ -0,0 +1,11 @@
+require 'nokogiri'
+
+
+page = Nokogiri::HTML(open("html/directory.html"))   
+
+page.css('a').each do |link|
+
+	if link['href'] and link['href'][0,55] === 'https://www.zomato.com/bangalore/directory/restaurants-'
+		puts link['href']
+	end
+end
\ No newline at end of file