python练习抓取web页面

时间：2010-09-25 来源：night85

from urllib import urlretrieve def firstNonBlank(lines):
    for eachLine in lines:
        if not eachLine.strip():
            continue
    else:
        return eachLine

def firstLast(webpage):
    f=open(webpage)
    lines=f.readlines()
    f.close
    print firstNonBlank(lines),
    lines.reverse()
    print firstNonBlank(lines),

def download(url= 'http://search.51job.com/jobsearch/advance_search.php',process=firstLast):
    try:
        retval = urlretrieve(url) [0]
    except IOError:
        retval = None
    if retval:
        process(retval)

if __name__ == '__main__':
    download()

相关阅读更多 +