python web编程-web客户端编程

  1 #!/usr/bin/env python
  2 
  3 from sys import argv
  4 from os import makedirs, unlink, sep
  5 from os.path import isdir, exists, dirname, splitext
  6 from string import replace, find, lower
  7 from htmllib import HTMLParser
  8 from urllib import urlretrieve
  9 from urlparse import urlparse, urljoin
 10 from formatter import DumbWriter, AbstractFormatter
 11 from cStringIO import StringIO
 12 
 13 class Retriever(object):    # download Web pages
 14 
 15     def __init__(self, url):
 16         self.url = url
 17         self.file = self.filename(url)
 18 
 19     def filename(self, url, deffile=‘index.htm‘):
 20         parsedurl = urlparse(url, ‘http:‘, 0)  # parse path
 21         path = parsedurl[1] + parsedurl[2]
 22         ext = splitext(path)
 23         if ext[1] == ‘‘:
 24             if path[-1] == ‘/‘:
 25                 path += deffile
 26             else:
 27                 path += ‘/‘ + deffile
 28         ldir = dirname(path)    # local directory
 29     if sep != ‘/‘:        # os-indep. path separator
 30         ldir = replace(ldir, ‘,‘, sep)
 31         if not isdir(ldir):      # create archive dir if nec.
 32             if exists(ldir): unlink(ldir)
 33             makedirs(ldir)
 34         return path
 35 
 36     def download(self):        # download Web page
 37         try:
 38             retval = urllib.urlretrieve(self.url, self.file)
 39         except IOError:
 40             retval = (‘*** ERROR: invalid URL "%s"‘ %  41                 self.url, )
 42         return retval
 43 
 44     def parseAndGetLinks(self):    # pars HTML, save links
 45         self.parser = HTMLParser(AbstractFormatter(  46             DumbWriter(StringIO())))
 47         self.parser.feed(open(self.file).read())
 48         self.parser.close()
 49         return self.parse.anchorlist
 50 
 51 class Crawler(object):        # manage entire crawling process
 52 
 53     count = 0            # static downloaded page counter
 54 
 55     def __init__(self, url):
 56         self.q = [url]
 57         self.seen = []
 58         self.dom = urlparse(url)[1]
 59 
 60     def getPage(self, url):
 61         r = Retriever(url)
 62         retval = r.download()
 63         if retval[0] == ‘*‘:     # error situation, do not parse
 64             print retval, ‘... skipping parse‘
 65             return
 66         Crawler.count = Crawler.count + 1
 67         print ‘\n(‘, Crawler.count, ‘)‘
 68         print ‘URL:‘, url
 69         print ‘FILE:‘, retval[0]
 70         self.seen.append(url)
 71 
 72         links = r.parseAndGetLinks()  # get and process links
 73         for eachLink in links:
 74             if eachLink[:4] != ‘http‘ and  75                     find(eachLink, ‘://‘) == -1:
 76                 eachLink = urljoin(url, eachLink)
 77             print ‘* ‘, eachLink,
 78 
 79             if find(lower(eachLink), ‘mailto:‘) != -1:
 80                 print ‘... discarded, mailto link‘
 81                 continue
 82 
 83             if eachLink not in self.seen:
 84                 if find(eachLink, self.dom) == -1:
 85                     print ‘... discarded, not in domain‘
 86                 else:
 87                     if eachLink not in self.q:
 88                         self.q.append(eachLink)
 89                         print ‘... new, added to Q‘
 90                     else:
 91                         print ‘... discarded, already in Q‘
 92             else:
 93                     print ‘... discarded, already processed‘
 94 
 95     def go(self):                # process links in queue
 96         while self.q:
 97             url = self.q.pop()
 98             self.getPage(url)
 99 
100 def main():
101     if len(argv) > 1:
102         url = argv[1]
103     else:
104         try:
105             url = raw_input(‘Enter starting URL: ‘)
106         except (KeyboardInterrupt, EOFError):
107             url = ‘‘
108 
109     if not url: return
110     robot = Crawler(url)
111     robot.go()
112 
113 if __name__ == ‘__main__‘:
114     main()