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