scrapy example

scrapy.py

class MySpider(BaseSpider):
    name = 'myspider'
    start_urls = (
        'http://example.com/page1',
        'http://example.com/page2',
        )

    def parse(self, response):
        # collect `item_urls`
        for item_url in item_urls:
            yield Request(url=item_url, callback=self.parse_item)

    def parse_item(self, response):
        item = MyItem()
        # populate `item` fields
        yield Request(url=item_details_url, meta={'item': item},
            callback=self.parse_details)

    def parse_details(self, response):
        item = response.meta['item']
        # populate more `item` fields
        return item
#该代码片段来自于: http://www.sharejs.com/codes/python/6398