scrapy spider及其子类

scrapy crawl myspider -a category=electronics

import scrapy

class MySpider(Spider):
    name = ‘myspider‘

    def __init__(self, category=None, *args, **kwargs):
        super(MySpider, self).__init__(*args, **kwargs)
        self.start_urls = [‘http://www.example.com/categories/%s‘ % category]
        # ...

def start_requests(self):
    return [scrapy.FormRequest("http://www.example.com/login",
                               formdata={‘user‘: ‘john‘, ‘pass‘: ‘secret‘},
                               callback=self.logged_in)]

def logged_in(self, response):
    # here you would extract links to follow and return Requests for
    # each of them, with another callback
    pass

import scrapy

class MySpider(scrapy.Spider):
    name = ‘example.com‘
    allowed_domains = [‘example.com‘]
    start_urls = [
        ‘http://www.example.com/1.html‘,
        ‘http://www.example.com/2.html‘,
        ‘http://www.example.com/3.html‘,
    ]

    def parse(self, response):
        self.log(‘A response from %s just arrived!‘ % response.url)

import scrapy

class MySpider(scrapy.Spider):
    name = ‘example.com‘
    allowed_domains = [‘example.com‘]
    start_urls = [
        ‘http://www.example.com/1.html‘,
        ‘http://www.example.com/2.html‘,
        ‘http://www.example.com/3.html‘,
    ]

    def parse(self, response):
        self.log(‘A response from %s just arrived!‘ % response.url)

import scrapy
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor

class MySpider(CrawlSpider):
    name = ‘example.com‘
    allowed_domains = [‘example.com‘]
    start_urls = [‘http://www.example.com‘]

    rules = (
        # 提取匹配 ‘category.php‘ (但不匹配 ‘subsection.php‘) 的链接并跟进链接(没有callback意味着follow默认为True)
        Rule(LinkExtractor(allow=(‘category\.php‘, ), deny=(‘subsection\.php‘, ))),

        # 提取匹配 ‘item.php‘ 的链接并使用spider的parse_item方法进行分析
        Rule(LinkExtractor(allow=(‘item\.php‘, )), callback=‘parse_item‘),
    )

    def parse_item(self, response):
        self.log(‘Hi, this is an item page! %s‘ % response.url)

        item = scrapy.Item()
        item[‘id‘] = response.xpath(‘//td[@id="item_id"]/text()‘).re(r‘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 import log
from scrapy.contrib.spiders import XMLFeedSpider
from myproject.items import TestItem

class MySpider(XMLFeedSpider):
    name = ‘example.com‘
    allowed_domains = [‘example.com‘]
    start_urls = [‘http://www.example.com/feed.xml‘]
    iterator = ‘iternodes‘ # This is actually unnecessary, since it‘s the default value
    itertag = ‘item‘

    def parse_node(self, response, node):
        log.msg(‘Hi, this is a <%s> node!: %s‘ % (self.itertag, ‘‘.join(node.extract())))

        item = TestItem()
        item[‘id‘] = node.xpath(‘@id‘).extract()
        item[‘name‘] = node.xpath(‘name‘).extract()
        item[‘description‘] = node.xpath(‘description‘).extract()
        return item

from scrapy import log
from scrapy.contrib.spiders import CSVFeedSpider
from myproject.items import TestItem

class MySpider(CSVFeedSpider):
    name = ‘example.com‘
    allowed_domains = [‘example.com‘]
    start_urls = [‘http://www.example.com/feed.csv‘]
    delimiter = ‘;‘
    quotechar = "‘"
    headers = [‘id‘, ‘name‘, ‘description‘]

    def parse_row(self, response, row):
        log.msg(‘Hi, this is a row!: %r‘ % row)

        item = TestItem()
        item[‘id‘] = row[‘id‘]
        item[‘name‘] = row[‘name‘]
        item[‘description‘] = row[‘description‘]
        return item

from scrapy.contrib.spiders import SitemapSpider

class MySpider(SitemapSpider):
    sitemap_urls = [‘http://www.example.com/sitemap.xml‘]
    sitemap_rules = [
        (‘/product/‘, ‘parse_product‘),
        (‘/category/‘, ‘parse_category‘),
    ]

    def parse_product(self, response):
        pass # ... scrape product ...

    def parse_category(self, response):
        pass # ... scrape category ...

from scrapy.contrib.spiders import SitemapSpider

class MySpider(SitemapSpider):
    sitemap_urls = [‘http://www.example.com/robots.txt‘]
    sitemap_rules = [
        (‘/shop/‘, ‘parse_shop‘),
    ]

    other_urls = [‘http://www.example.com/about‘]

    def start_requests(self):
        requests = list(super(MySpider, self).start_requests())
        requests += [scrapy.Request(x, self.parse_other) for x in self.other_urls]
        return requests

    def parse_shop(self, response):
        pass # ... scrape shop here ...

    def parse_other(self, response):
        pass # ... scrape other here ...