python爬虫----（3. scrapy框架，简单应用）

scrapy startproject getblog

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

from scrapy.item import Item, Field

class BlogItem(Item):
    title = Field()
    desc = Field()

# coding=utf-8

from scrapy.spider import Spider
from getblog.items import BlogItem
from scrapy.selector import Selector


class BlogSpider(Spider):
    # 标识名称
    name = 'blog'
    # 起始地址
    start_urls = ['http://www.cnblogs.com/']

    def parse(self, response):
        sel = Selector(response) # Xptah 选择器
        # 选择所有含有class属性，值为‘post_item’的div 标签内容
        # 下面的 第2个div 的 所有内容
        sites = sel.xpath('//div[@class="post_item"]/div[2]')
        items = []
        for site in sites:
            item = BlogItem()
            # 选取h3标签下，a标签下，的文字内容 ‘text()’
            item['title'] = site.xpath('h3/a/text()').extract()
            # 同上，p标签下的 文字内容 ‘text()’
            item['desc'] = site.xpath('p[@class="post_item_summary"]/text()').extract()
            items.append(item)
        return items

scrapy crawl blog  # 即可

# 输出文件位置
FEED_URI = 'blog.xml'
# 输出文件格式 可以为 json，xml，csv
FEED_FORMAT = 'xml'