acrymble

if char == '<':
    # do something
elif char == '>':
    # do another thing
else:
    # do something completely different

acrymble

# obo.py
 
def stripTags(pageContents): 
    startLoc = pageContents.find("<hr/><h2>")
 
    pageContents = pageContents[startLoc:]

    inside = 0
    text = ''
    for char in pageContents:

acrymble

inside = 1

acrymble

f = open('helloworld.txt','w')
f.write('hello world')
f.close()

acrymble

# string-to-list.py

# some strings
s1 = 'hello world'
s2 = 'howdy world'

# list of characters
charlist = []
for char in s1:
    charlist.append(char)

acrymble

#html-to-list1.py
import urllib2, obo

url = 'http://www.oldbaileyonline.org/print.jsp?div=t17800628-33'

response = urllib2.urlopen(url)
html = response.read()
text = obo.stripTags(html)
wordlist = text.split()
print wordlist[0:120]

acrymble

['BENJAMIN', 'BOWSEY,', 'Breaking', 'Peace', '>', 
'riot,', '28th', 'June', '1780.', '324.', 'BENJAMIN', 
'BOWSEY', '(a', 'blackmoor', ')', 'was', 'indicted', 
'for', 'that', 'he', 'together', 'with', 'five', 
'hundred', 'other', 'persons', 'and', 'more,', 'did,', 
'unlawfully,', 'riotously,', 'and', 'tumultuously', 
'assemble', 'on', 'the', '6th', 'of', 'June', 'to', 
'the', 'disturbance', 'of', 'the', 'public', 'peace', 
'and', 'did', 'begin', 'to', 'demolish', 'and', 'pull', 
'down', 'the', 'dwelling', 'house', 'of', 'Richard', 

acrymble

#html-to-list1.py
import urllib2
import dh
 
url = 'http://www.oldbaileyonline.org/print.jsp?div=t17800628-33'
 
response = urllib2.urlopen(url)
xhtml = response.read()
text = dh.stripTags(xhtml).lower()    #add the string method here.
wordlist = text.split()

acrymble

#html-to-list1.py
import urllib2, obo
 
url = 'http://www.oldbaileyonline.org/print.jsp?div=t17800628-33'
 
response = urllib2.urlopen(url)
html = response.read()
text = obo.stripTags(html).lower()    #add the string method here.
wordlist = text.split()

acrymble

text = text.replace('[', '')
text = text.replace(']', '')
text = text.replace(',', '')
#etc...