我们来看一个例子: 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.logger.info('A response from %s just arrived!', response.url)
从单个回调返回多个请求和项目: 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):
for h3 in response.xpath('//h3').getall():
yield {"title": h3}
for href in response.xpath('//a/@href').getall():
yield scrapy.Request(response.urljoin(href), self.parse)
而不是 import scrapy
from myproject.items import MyItem
class MySpider(scrapy.Spider):
name = 'example.com'
allowed_domains = ['example.com']
def start_requests(self):
yield scrapy.Request('http://www.example.com/1.html', self.parse)
yield scrapy.Request('http://www.example.com/2.html', self.parse)
yield scrapy.Request('http://www.example.com/3.html', self.parse)
def parse(self, response):
for h3 in response.xpath('//h3').getall():
yield MyItem(title=h3)
for href in response.xpath('//a/@href').getall():
yield scrapy.Request(response.urljoin(href), self.parse) |
Archiver|手机版|笨鸟自学网 ( 粤ICP备20019910号 )
GMT+8, 2024-9-8 09:32 , Processed in 0.020042 second(s), 17 queries .