docker90

import sys
from HTMLParser import HTMLParser

class TextExtractor(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.recording = True
        self.output = []

    def handle_starttag(self, tag, attrs):
        # Ignore these tags and everything inside them
        if tag in ['script', 'style', 'head', 'title', 'meta', 'noscript']:
            self.recording = False

    def handle_endtag(self, tag):
        # Resume recording after the block ends
        if tag in ['script', 'style', 'head', 'title', 'meta', 'noscript']:
            self.recording = True

    def handle_data(self, data):
        if self.recording:
            # Clean and add the text to our list
            text = data.strip()
            if text:
                self.output.append(text)

if __name__ == "__main__":
    parser = TextExtractor()
    parser.feed(sys.stdin.read())
    print " ".join(parser.output)