Searching for more than one word in multiple files

[grantstech]

I have successfully created a program that searches for a word in multiple files but now I need to be able to search by more than one word. I have add code from a previous discussion to my original program but I am unsure how they should fit together. Can someone clear this up for me?

#!C:\PYTHON25\PYTHON.EXE
 
import os
import re
dir_name= r'c:\Python25\books\books\books'
word=raw_input("Enter a word to search for: ")
word2=raw_input("Enter a second word to search for: ")
keyList = ['word', 'word2']
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name) if os.path.isfile(os.path.join(dir_name, fn))]
for file_name in entryList:
    for line in file(file_name).readlines():
        if word in line:
            print line           
patt = re.compile('|'.join(keyList), re.IGNORECASE)
for fn in dir_name:
    f = open(fn)
    for line in f:
        if patt.search(line.lower()):
            print line
    f.close()
 

[bartonc]

I have successfully created a program that searches for a word in multiple files but now I need to be able to search by more than one word. I have add code from a previous discussion to my original program but I am unsure how they should fit together. Can someone clear this up for me?

#!C:\PYTHON25\PYTHON.EXE
 
import os
import re
dir_name= r'c:\Python25\books\books\books'
word=raw_input("Enter a word to search for: ")
word2=raw_input("Enter a second word to search for: ")
keyList = ['word', 'word2']
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name) if os.path.isfile(os.path.join(dir_name, fn))]
for file_name in entryList:
    for line in file(file_name).readlines():
        if word in line:
            print line           
patt = re.compile('|'.join(keyList), re.IGNORECASE)
for fn in dir_name:
    f = open(fn)
    for line in f:
        if patt.search(line.lower()):
            print line
    f.close()
 

Here's one way:

import os
import re
dir_name = r'c:\Python25\books\books\books'
 
##word2 = raw_input("Enter a second word to search for: ")
###removed quotes#
##keyList = [word, word2]
 
def FindWord(word, fileList):
    for file_name in fileList:
        for line in file(file_name).readlines():
            if word in line:
                print line
 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in dir_name:
        f = open(fn)
        for line in f.readlines(): # added .readlines()
            if patt.search(line.lower()): # probably don't need .lower()
                print line
        f.close()
 
 
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name)
             if os.path.isfile(os.path.join(dir_name, fn))]
 
words = raw_input("Enter one or more words to search for: ")
keyList = words.split()
if len(keylist) > 1:
    FindWords(keylist, entryList)
else:
    FindWord(words, entryList)
 

[grantstech]

Here is what I have now. It searchs on just fine but when I add a second word it gives me an error. I added a print statement to see if it was splitting the input and it is. I have listed the error I keep getting at the bottom. I can't figure out what is wrong.
Thanks for all your help.

 
import os
import re
dir_name = r'c:\Python25\books\books\books'
 
 
def FindWord(word, fileList):
    for file_name in fileList:
        for line in file(file_name).readlines():
            if word in line:
                print line
 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in dir_name:
        f = open(fn)
        for line in f.readlines(): 
            if patt.search(line): 
                print line
        f.close()
 
 
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name)
             if os.path.isfile(os.path.join(dir_name, fn))]
 
words = raw_input("Enter one or more words to search for: ")
keyList = words.split()
print keyList
if len(keyList) > 1:
    FindWords(words, entryList)
else:
    FindWord(words, entryList)
 

Enter one or more words to search for: bird goat tree
['bird', 'goat', 'tree']

Traceback (most recent call last):
File "C:/Python25/searchtest.py", line 29, in <module>
FindWords(words, entryList)
File "C:/Python25/searchtest.py", line 15, in FindWords
f = open(fn)
IOError: [Errno 2] No such file or directory: 'c'

[bvdet]

Here is what I have now. It searchs on just fine but when I add a second word it gives me an error. I added a print statement to see if it was splitting the input and it is. I have listed the error I keep getting at the bottom. I can't figure out what is wrong.
Thanks for all your help.

 
import os
import re
dir_name = r'c:\Python25\books\books\books'
 
 
def FindWord(word, fileList):
    for file_name in fileList:
        for line in file(file_name).readlines():
            if word in line:
                print line
 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in dir_name:
        f = open(fn)
        for line in f.readlines(): 
            if patt.search(line): 
                print line
        f.close()
 
 
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name)
             if os.path.isfile(os.path.join(dir_name, fn))]
 
words = raw_input("Enter one or more words to search for: ")
keyList = words.split()
print keyList
if len(keyList) > 1:
    FindWords(words, entryList)
else:
    FindWord(words, entryList)
 

Enter one or more words to search for: bird goat tree
['bird', 'goat', 'tree']

Traceback (most recent call last):
File "C:/Python25/searchtest.py", line 29, in <module>
FindWords(words, entryList)
File "C:/Python25/searchtest.py", line 15, in FindWords
f = open(fn)
IOError: [Errno 2] No such file or directory: 'c'

You have left out some code. Look at this and then look at your code:

>>> dir_name = r'c:\Python25\books\books\books'
>>> for fn in dir_name:
...     print fn
...     
c
:
\
P
y
t
h
o
n
2
5
\
b
o
o
k
s
\
b
o
o
k
s
\
b
o
o
k
s
>>> 

[bartonc]

Here is what I have now. It searchs on just fine but when I add a second word it gives me an error. I added a print statement to see if it was splitting the input and it is. I have listed the error I keep getting at the bottom. I can't figure out what is wrong.
Thanks for all your help.

 
import os
import re
dir_name = r'c:\Python25\books\books\books'
 
 
def FindWord(word, fileList):
    for file_name in fileList:
        for line in file(file_name).readlines():
            if word in line:
                print line
 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in dir_name:
        f = open(fn)
        for line in f.readlines(): 
            if patt.search(line): 
                print line
        f.close()
 
 
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name)
             if os.path.isfile(os.path.join(dir_name, fn))]
 
words = raw_input("Enter one or more words to search for: ")
keyList = words.split()
print keyList
if len(keyList) > 1:
    FindWords(words, entryList)
else:
    FindWord(words, entryList)
 

Enter one or more words to search for: bird goat tree
['bird', 'goat', 'tree']

Traceback (most recent call last):
File "C:/Python25/searchtest.py", line 29, in <module>
FindWords(words, entryList)
File "C:/Python25/searchtest.py", line 15, in FindWords
f = open(fn)
IOError: [Errno 2] No such file or directory: 'c'

My bad. Sorry. It should be:

 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in fileList:
        f = open(fn)
        for line in f.readlines(): 
            if patt.search(line): 
                print line
        f.close()
 

[grantstech]

Thanks guys.
I got it where it is searching for all the words but I need to fine tune it some more.
First of all, when I put in a word like "eat", it is finding everything with those letters in it like "beat". Is there a way to make it only pull up the exact word?

Also it is bring up all of the lines that have one of the words in it. Is there a way to change it so that it only prints the lines that have all of the words in it?

[Smygis]

#!C:\PYTHON25\PYTHON.EXE

Shuld always be

#!/usr/bin/env python

And never anything else.

Unlike windows who executes files after ther file extention *nix systems reads the first line of every file before its executed.

And if that line begins with #! the rest of the file is sent as an argument to the specified enviroment. in our case, python.

[bartonc]

Thanks guys.
I got it where it is searching for all the words but I need to fine tune it some more.
First of all, when I put in a word like "eat", it is finding everything with those letters in it like "beat". Is there a way to make it only pull up the exact word?

Also it is bring up all of the lines that have one of the words in it. Is there a way to change it so that it only prints the lines that have all of the words in it?

It would be very helpful if you would get in the habit of posting the working code (especially if you still have questions). It helps others figure out this type of problem when they get stuck and it helps us see what the heck you're talking about.

That said:
The "fine tuning" comes down to learning the Regular Expression language and I'm not sure that I'm reading to start calling this the Python/Regex Forum, just yet. Regular-Expression.info is a good place to start with that.

[grantstech]

It would be very helpful if you would get in the habit of posting the working code (especially if you still have questions). It helps others figure out this type of problem when they get stuck and it helps us see what the heck you're talking about.

That said:
The "fine tuning" comes down to learning the Regular Expression language and I'm not sure that I'm reading to start calling this the Python/Regex Forum, just yet. Regular-Expression.info is a good place to start with that.

It's not much different that is listed above:

import os
import re
dir_name = r'c:\Python25\books\books\books'
 
def FindWord(word, fileList):
    for file_name in fileList:
        for line in file(file_name).readlines():
            if word in line:
                print line
 
def FindWords(wordList, fileList):
    patt = re.compile('|'.join(wordList), re.IGNORECASE)
    for fn in fileList:
        f = open(fn)
        for line in f.readlines(): 
            if patt.search(line): 
                print line
        f.close()
entryList = [os.path.join(dir_name, fn) for fn in os.listdir(dir_name)
            if os.path.isfile(os.path.join(dir_name, fn))]
 
words = raw_input("Enter one or more words to search for: ")
keyList = words.split()
if len(keyList) > 1:
    FindWords(keyList, entryList)
else:
    FindWord(words, entryList)
 

[bvdet]

Given a file name and a key word list, this function will print any line that contains a word in the key word list:

def matchAnyWord(fn, keyList):
    patt = re.compile('(?<![a-z])%s(?![a-z])' % '(?![a-z])|(?<![a-z])'.join(keyList), re.IGNORECASE)
    f = open(fn)
    for line in f:
        if patt.search(line.lower()):
            print line
    f.close()

Given a file name and a key word list, this function will print any line that contains all of the words in the key word list:

def matchAllWords(fn, keyList):
    pattList = [re.compile('(?<![a-z])%s(?![a-z])' % key) for key in keyList]
    f = open(fn)
    for line in f:
        matchList = []
        for patt in pattList:
            matchList.append(patt.search(line.lower()))
        print matchList
        if None not in matchList:
            print line
    f.close()

[grantstech]

Great, thanks, bvdet. I'll try to incorporate that.

Given a file name and a key word list, this function will print any line that contains a word in the key word list:

def matchAnyWord(fn, keyList):
    patt = re.compile('(?<![a-z])%s(?![a-z])' % '(?![a-z])|(?<![a-z])'.join(keyList), re.IGNORECASE)
    f = open(fn)
    for line in f:
        if patt.search(line.lower()):
            print line
    f.close()

Given a file name and a key word list, this function will print any line that contains all of the words in the key word list:

def matchAllWords(fn, keyList):
    pattList = [re.compile('(?<![a-z])%s(?![a-z])' % key) for key in keyList]
    f = open(fn)
    for line in f:
        matchList = []
        for patt in pattList:
            matchList.append(patt.search(line.lower()))
        print matchList
        if None not in matchList:
            print line
    f.close()

[bvdet]

Here is an interactive exercise:

>>> keyList = ['thread', 'needle']
>>> patt = re.compile('(?<![a-z])%s(?![a-z])' % '(?![a-z])|(?<![a-z])'.join(keyList), re.IGNORECASE)
>>> patt.search('The thread was threaded through several needles')
<_sre.SRE_Match object at 0x00DB6138>
>>> print patt.search('The threads were threaded through several needles')
None
>>> pattList = [re.compile('(?<![a-z])%s(?![a-z])' % key) for key in keyList]
>>> for patt in pattList:
...     print patt.search('The thread was threaded through several needles')
...     
<_sre.SRE_Match object at 0x00DB62F8>
None
>>> for patt in pattList:
...     print patt.search('The thread was threaded through a needle')
...     
<_sre.SRE_Match object at 0x00DB6288>
<_sre.SRE_Match object at 0x00DB6288>
>>> 

The re expression was modified to exclude matches if a key word was preceded or followed by any letter in the set '[a-z]'.