Created
June 10, 2009 14:33
-
-
Save badri/127244 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data = {} | |
c2t = re.compile('to Text Ratio\s+: ([\d\.]+) %\s+</td>') | |
page_size = re.compile('Page Size</span></td>\s+<td class="linkcrfill1" width="98%" style="padding:0px 7px 0px 7px;" >\s+: (\d+) Bytes') | |
code_size = re.compile('Code\s+Size </span></td>\s+<td class="linkcrfill1" style="padding:0px 7px 0px 7px;">\s+: (\d+) Bytes') | |
text_size = re.compile('Text\s+Size </span></td>\s+<td class="linkcrfill1" style="padding:0px 7px 0px 7px;" >\s+: (\d+) Bytes') | |
words = words.strip().split("\n") | |
for word in words: | |
word = re.sub(' ', '%2520', word) | |
#word = re.sub(r'\'', '%27', word) | |
uri = 'http://www.rankquest.com/tools/Text-Ratio.php?url=http%3A%2F%2Fdictionary.reference.com%2Fbrowse%2F' + word + '&Submit2=Check+Ratio' | |
content = (urllib2.urlopen(uri)).read() | |
t = {} | |
t['c2t'] = c2t.findall(content)[0] | |
t['pagesize'] = page_size.findall(content)[0] | |
t['codesize'] = code_size.findall(content)[0] | |
t['textsize'] = text_size.findall(content)[0] | |
data[word] = t |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment