How to search text on an html page

**dbphydb** · May 13 '10, 04:51 AM

Hi,
I want to search for a particular text on an html page ---> Build Complete
Further execution should be only if the build is successful which is denoted by the text 'Build Complete' on the webpage.

Code:

URL = "http://11.12.13.27:8080/cruisecontrol"

from urllib2 import urlopen
from HTMLParser import HTMLParser

import re

# Fetching links using HTMLParser
def get_links(url):
    parser = MyHTMLParser()
    parser.feed(urlopen(url).read())
    parser.close()
    return parser.links

# Build url for Deploy page
def get_deploy_url():
    url = URL + "/buildresults/Poker-TTM_%s_nightly_build" % branch
    print url
    check_re = re.compile(r"/Build Complete/")
    print check_re
    if check_re.search(url):
        print "hello"
        for link in get_links(url):
            if link["href"].startswith("Deploy"):
                return "%s/%s" % (URL, link["href"])
        print link["href"]

# Build url for Destination page
def get_destination_url():
    url = get_deploy_url()
    print url
    destination_re = re.compile(r"%s" % destination)
    for link in get_links(url):
        if destination_re.search(link["href"]):
            return "http://11.12.13.27:8080/cruisecontrol/" + link["href"]

# Parsing HTML pages 
class MyHTMLParser(HTMLParser):
    def __init__(self, *args, **kwd):
        HTMLParser.__init__(self, *args, **kwd)
        self.links = []

    def handle_starttag(self, tag, attrs):
        if tag == "a":
            attrs = dict(attrs)
            if "href" in attrs:
                self.links.append(dict(attrs))

    def handle_endtag(self, tag):
        pass

if __name__ == "__main__":
    # Read the branch name and the test destination to deploy on
    lines = [x.split(':') for x in open("branch_dest.txt")]
    print lines
    branch = "%s" % lines[0][1].strip()
    print branch
    destination = "%s" % lines[1][1].strip()
    print destination
    
    final_url = get_destination_url()
    if final_url is None:
        print "Could not find a destination to deploy"
    else:
        print final_url

I am getting the below error

Code:

Traceback (most recent call last):
  File "C:\deploy_input.py", line 61, in <module>
    final_url = get_destination_url()
  File "C:\deploy_input.py", line 33, in get_destination_url
    for link in get_links(url):
  File "C:\deploy_input.py", line 11, in get_links
    parser.feed(urlopen(url).read())
  File "C:\Python26\lib\urllib2.py", line 126, in urlopen
    return _opener.open(url, data, timeout)
  File "C:\Python26\lib\urllib2.py", line 382, in open
    req.timeout = timeout
AttributeError: 'NoneType' object has no attribute 'timeout'

Help!