A linux bash shell script for searching imdb movies by name and download all relevant title ( movie ) pages. Then perform rating extraction on each of the pages and show in console.

imdbMovieSearchRatingExtract.sh

#!/bin/bash

#===============================================================================#
# Author:	Asif Ahmed		                                        #
# Version:	0.2					                        #
# Site:         http://quickgrid.blogspot.com                                   #
# Description:  IMDB Movie Search and Rating Extraction	                        #
# Note:		This code is highly dependent on the current page structure or, #
#	      	html design of IMDB. If it changes the code will break.         #
#===============================================================================#


# Read the movie name
read searchText

# Download the result page for the specified search
wget -O "$searchText-search.html" "http://www.imdb.com/find?q=$searchText"


# Run another regex to get the movie titles div and write the data to another file to avoid link filename mismatch
sed -e '/Titles<\/h3>/,/findMoreMatches/!d' "$searchText-search.html" > "partialContentFile.txt"



# Define the file where the links will be stored
writeLinksFileName="filesToDownload.txt"


# Get the movie links from html file
grep -E -w -o "\/title\/[a-zA-Z0-9]+\/" "partialContentFile.txt" > $writeLinksFileName

# Get the movie names
grep -P -o "(?<=>)([a-zA-Z0-9&: _-]+)(?=<\/a>[\(\) a-zA-Z0-9 _-]*\([0-9]+\))" "partialContentFile.txt" > "movieNames.txt" 

# Get the movie years
grep -P -o "(?<=<\/a> )(\([0-9]+\))(?= )" "partialContentFile.txt" > "movieYears.txt" 

# Delete contents of file
> "movieNameYear.txt"

# Use different file descriptors to read from and work with two files
while read -r -u3 movieName; read -r -u4 movieYear;
do 
	echo "$movieName" "$movieYear" >> "movieNameYear.txt"
done 3<movieNames.txt 4<movieYears.txt


# Read from the file that was written to
j=0

while read line
do
	repline=$line
	
	# Replace file name spaces with underscore
	fixedline=${repline// /_}	

	movieNameYear_array[j]=$fixedline
	#echo ${movieNameYear_array[j]}
	j=$(( j + 1 ))
done < "movieNameYear.txt"



# Since the link are duplicated due 

moviefoldername=movies
mkdir $moviefoldername

i=0
k=0

while read line
do
	temp=$(( $i % 2 )) 
	
	# Temporary fix when file name or file year was not extracted correctly 
	if [ $j -eq $k ]; then
		break
	fi
	
	if [ $temp -eq 0 ]; then
		
		# Each of the resultant files are downloaded here, Now read and perform rating extraction from it
		wget -O "$moviefoldername/${movieNameYear_array[k]}" "http://www.imdb.com$line"
		k=$(( k + 1 ))

	fi

	i=$(( i + 1 ))

done < $writeLinksFileName


# Now print the files in the movies directory

for fileName in `ls $moviefoldername/`
do
	#echo "$fileName"
	
	# Sample rating tag block
	#<span itemprop="ratingValue">6.4</span></strong>

	echo "Rating of: $fileName"	
	grep -P -o "(?<=<span itemprop=\"ratingValue\">)([0-9][.]?[0-9]?)(?=<\/span><\/strong>)" "$moviefoldername/$fileName" 
	echo "===================" 

done