Using bs4 to extract text in html files

Question

Want to extract text from my html files. if I use below for a specific file:

import bs4, sys
from urllib import urlopen
#filin = open(sys.argv[1], 'r')
filin = '/home/iykeln/Desktop/R_work/file1.html' 
webpage = urlopen(filin).read().decode('utf-8')
soup = bs4.BeautifulSoup(webpage)
for node in soup.findAll('html'):
    print u''.join(node.findAll(text=True)).encode('utf-8')

it will work. But trying below for non specific files using open(sys.argv[1], 'r'):

import bs4, sys
from urllib import urlopen
filin = open(sys.argv[1], 'r')
#filin = '/home/iykeln/Desktop/R_work/file1.html' 
webpage = urlopen(filin).read().decode('utf-8')
soup = bs4.BeautifulSoup(webpage)
for node in soup.findAll('html'):
    print u''.join(node.findAll(text=True)).encode('utf-8')

OR

import bs4, sys
from urllib import urlopen
with open(sys.argv[1], 'r') as filin:
    webpage = urlopen(filin).read().decode('utf-8')
    soup = bs4.BeautifulSoup(webpage)
    for node in soup.findAll('html'):
        print u''.join(node.findAll(text=True)).encode('utf-8')

I will be getting errors below:

Traceback (most recent call last):
  File "/home/iykeln/Desktop/py/clean.py", line 5, in <module>
    webpage = urlopen(filin).read().decode('utf-8')
  File "/usr/lib/python2.7/urllib.py", line 87, in urlopen
    return opener.open(url)
  File "/usr/lib/python2.7/urllib.py", line 180, in open
    fullurl = unwrap(toBytes(fullurl))
  File "/usr/lib/python2.7/urllib.py", line 1057, in unwrap
    url = url.strip()
AttributeError: 'file' object has no attribute 'strip'

Solution

You shouldn't call open, just pass the file name to the urlopen:

import bs4, sys
from urllib import urlopen

webpage = urlopen(sys.argv[1]).read().decode('utf-8')
soup = bs4.BeautifulSoup(webpage)
for node in soup.findAll('html'):
    print u''.join(node.findAll(text=True)).encode('utf-8')

FYI, you don't need urllib for opening local files:

import bs4, sys

with open(sys.argv[1], 'r') as f:
    webpage = f.read().decode('utf-8')

soup = bs4.BeautifulSoup(webpage)
for node in soup.findAll('html'):
    print u''.join(node.findAll(text=True)).encode('utf-8')

Hope that helps.