apirefscrape.py 文件源码

def scrape_url(url):
    #url = 'api-ref-compute-v2.1.html'
    page = requests.get('http://developer.openstack.org/' + url)
    tree = html.fromstring(page.content)
    #Create a list of HTTP verbs
    verbs = tree.xpath('//a[@class="operation-anchor"]/following::span[1]/text()')
    operations = tree.xpath('//a[@class="operation-anchor"]/following::div[1]/text()')
    #Match up Verbs and Operations and output a printed list
    methods = zip(verbs, operations)
    print len(verbs)
    print len(operations)
    if len(verbs) == len(operations):
        for verbs, operations in methods:
            print verbs + ' ' + operations
    else:
        print "Number of verbs doesn't match number of operations for ", page.url