Python的Scrapy爬虫框架简单学习笔记

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'

dizzy@dizzy-pc:~$ scrapy shell "http://www.baidu.com/"

2014-08-21 04:09:11+0800 [scrapy] INFO: Scrapy 0.24.4 started (bot: scrapybot)
2014-08-21 04:09:11+0800 [scrapy] INFO: Optional features available: ssl, http11, django
2014-08-21 04:09:11+0800 [scrapy] INFO: Overridden settings: {'LOGSTATS_INTERVAL': 0}
2014-08-21 04:09:11+0800 [scrapy] INFO: Enabled extensions: TelnetConsole, CloseSpider, WebService, CoreStats, SpiderState
2014-08-21 04:09:11+0800 [scrapy] INFO: Enabled downloader middlewares: HttpAuthMiddleware, DownloadTimeoutMiddleware, UserAgentMiddleware, RetryMiddleware, DefaultHeadersMiddleware, MetaRefreshMiddleware, HttpCompressionMiddleware, RedirectMiddleware, CookiesMiddleware, ChunkedTransferMiddleware, DownloaderStats
2014-08-21 04:09:11+0800 [scrapy] INFO: Enabled spider middlewares: HttpErrorMiddleware, OffsiteMiddleware, RefererMiddleware, UrlLengthMiddleware, DepthMiddleware
2014-08-21 04:09:11+0800 [scrapy] INFO: Enabled item pipelines: 
2014-08-21 04:09:11+0800 [scrapy] DEBUG: Telnet console listening on 127.0.0.1:6024
2014-08-21 04:09:11+0800 [scrapy] DEBUG: Web service listening on 127.0.0.1:6081
2014-08-21 04:09:11+0800 [default] INFO: Spider opened
2014-08-21 04:09:12+0800 [default] DEBUG: Crawled (200) <GET http://www.baidu.com/> (referer: None)
[s] Available Scrapy objects:
[s]  crawler  <scrapy.crawler.Crawler object at 0xa483cec>
[s]  item    {}
[s]  request  <GET http://www.baidu.com/>
[s]  response  <200 http://www.baidu.com/>
[s]  settings  <scrapy.settings.Settings object at 0xa0de78c>
[s]  spider   <Spider 'default' at 0xa78086c>
[s] Useful shortcuts:
[s]  shelp()      Shell help (print this help)
[s]  fetch(req_or_url) Fetch request (or URL) and update local objects
[s]  view(response)  View response in a browser
 
>>> 
  # response.body 返回的所有内容
  # response.xpath('//ul/li') 可以测试所有的xpath内容
    More important, if you type response.selector you will access a selector object you can use to
query the response, and convenient shortcuts like response.xpath() and response.css() mapping to
response.selector.xpath() and response.selector.css()

scrapy shell 'http://scrapy.org' --nolog
# 参数 --nolog 没有日志

from scrapy import Spider
from scrapy_test.items import DmozItem
 
 
class DmozSpider(Spider):
  name = 'dmoz'
  allowed_domains = ['dmoz.org']
  start_urls = ['http://www.dmoz.org/Computers/Programming/Languages/Python/Books/',
         'http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/,'
         '']
 
  def parse(self, response):
    for sel in response.xpath('//ul/li'):
      item = DmozItem()
      item['title'] = sel.xpath('a/text()').extract()
      item['link'] = sel.xpath('a/@href').extract()
      item['desc'] = sel.xpath('text()').extract()
      yield item

scrapy crawl -o 'a.json' -t 'json'

scrapy genspider baidu baidu.com
 
# -*- coding: utf-8 -*-
import scrapy
 
 
class BaiduSpider(scrapy.Spider):
  name = "baidu"
  allowed_domains = ["baidu.com"]
  start_urls = (
    'http://www.baidu.com/',
  )
 
  def parse(self, response):
    pass

#coding=utf-8
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor
import scrapy
 
 
class TestSpider(CrawlSpider):
  name = 'test'
  allowed_domains = ['example.com']
  start_urls = ['http://www.example.com/']
  rules = (
    # 元组
    Rule(LinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))),
    Rule(LinkExtractor(allow=('item\.php', )), callback='pars_item'),
  )
 
  def parse_item(self, response):
    self.log('item page : %s' % response.url)
    item = scrapy.Item()
    item['id'] = response.xpath('//td[@id="item_id"]/text()').re('ID：(\d+)')
    item['name'] = response.xpath('//td[@id="item_name"]/text()').extract()
    item['description'] = response.xpath('//td[@id="item_description"]/text()').extract()
    return item

  >>> from scrapy.selector import Selector
  >>> from scrapy.http import HtmlResponse

from scrapy.exceptions import DropItem
 
class PricePipeline(object):
  vat_factor = 1.5
  def process_item(self, item, spider):
    if item['price']:
      if item['price_excludes_vat']:
        item['price'] *= self.vat_factor
    else:
      raise DropItem('Missing price in %s' % item)

import json
 
class JsonWriterPipeline(object):
  def __init__(self):
    self.file = open('json.jl', 'wb')
  def process_item(self, item, spider):
    line = json.dumps(dict(item)) + '\n'
    self.file.write(line)
    return item

from scrapy.exceptions import DropItem
 
class Duplicates(object):
  def __init__(self):
    self.ids_seen = set()
  def process_item(self, item, spider):
    if item['id'] in self.ids_seen:
      raise DropItem('Duplicate item found : %s' % item)
    else:
      self.ids_seen.add(item['id'])
      return item