[Scrapy-5] 常用爬虫Spiders

POST方式爬取数据

一般情况下使用Scrapy默认的方式就可以处理各种GET方式的数据爬取需求，当然有些场景是需要用户登录或者提供某些数据后使用POST请求才能获取到需要的数据。

class MySpider(scrapy.Spider):
    name = 'myspider'

    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

限定域名和处理日志

在Scrapy.Spider类中初始化了logger：

@property
def logger(self):
    logger = logging.getLogger(self.name)
    return logging.LoggerAdapter(logger, {'spider': self})

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.logger.info('A response from %s just arrived!', response.url)

Spider参数

在命令行下使用crawl命令启动爬虫的时候可以带参数，使用-a指定即可

scrapy crawl myspider -a category=electronics

可以通过__init__方法获取参数：

import scrapy

class MySpider(scrapy.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]
        # ...

Spider的init方法会获取任何的Spider的参数，并且将它们复制，作为Spider的属性，所以你可以直接将参数作为属性使用：

import scrapy

class MySpider(scrapy.Spider):
    name = 'myspider'

    def start_requests(self):
        yield scrapy.Request('http://www.example.com/categories/%s' % self.category)

CrawlSpider

这是最常用的爬取网络数据的爬虫，并且可以自定义一些列规则

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

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

    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(LinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))),

        # Extract links matching 'item.php' and parse them with the spider's method parse_item
        Rule(LinkExtractor(allow=('item\.php', )), callback='parse_item'),
    )

    def parse_item(self, response):
        self.logger.info('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

XMLFeedSpider example

from scrapy.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):
        self.logger.info('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

CSVFeedSpider example

from scrapy.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):
        self.logger.info('Hi, this is a row!: %r', row)

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