欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

python使用scrapy解析js示例

 更新時(shí)間：2014年01月23日 10:06:22   作者：  
這篇文章主要介紹了python使用scrapy解析js的示例，大家參考使用吧

復(fù)制代碼 代碼如下:

from selenium import selenium

class MySpider(CrawlSpider):
    name = 'cnbeta'
    allowed_domains = ['cnbeta.com']
    start_urls = ['http://www.dbjr.com.cn']

    rules = (
        # Extract links matching 'category.php' (but not matching 'subsection.php')
        # and follow links from them (since no callback means follow=True by default).
        Rule(SgmlLinkExtractor(allow=('/articles/.*\.htm', )),
             callback='parse_page', follow=True),

        # Extract links matching 'item.php' and parse them with the spider's method parse_item
    )

    def __init__(self):
        CrawlSpider.__init__(self)
        self.verificationErrors = []
        self.selenium = selenium("localhost", 4444, "*firefox", "http://www.dbjr.com.cn")
        self.selenium.start()

    def __del__(self):
        self.selenium.stop()
        print self.verificationErrors
        CrawlSpider.__del__(self)


    def parse_page(self, response):
        self.log('Hi, this is an item page! %s' % response.url)
        sel = Selector(response)
        from webproxy.items import WebproxyItem

        sel = self.selenium
        sel.open(response.url)
        sel.wait_for_page_to_load("30000")
        import time

        time.sleep(2.5)

相關(guān)文章

最新評(píng)論