爬取目标:糗事百科全部文章的内容和网址。
直接上代码:
items.py
#糗事百科自动抓取
class QSBKAutoItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
content = scrapy.Field()
link = scrapy.Field()
爬虫文件
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from testscrapy01.items import QSBKAutoItem
class QsbkautoSpider(CrawlSpider):
name = 'qsbkauto'
allowed_domains = ['qiushibaike.com']
start_urls = ['http://qiushibaike.com/']
rules = (
#指定链接提取的规律 r代表后面引号里面的字符均为非转义
#follow:是指爬取了之后,是否还继续从该页面提取链接,然后继续爬下去
Rule(LinkExtractor(allow=r'article'), callback='parse_item', follow=True),
)
def parse_item(self, response):
item = QSBKAutoItem()
#i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
#i['name'] = response.xpath('//div[@id="name"]').extract()
#i['description'] = response.xpath('//div[@id="description"]').extract()
item["content"] = response.xpath("//div[@class='content']/text()").extract()[0]
item["link"] = response.xpath("//link[@rel='canonical']/@href").extract()[0]
print("内容:",item["content"])
print("链接:",item["link"])
print("*************************************************************")
yield item
对以上代码的改进:
# coding=utf-8
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from testscrapy01.items import QSBKAutoItem
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
class QsbkautoSpider(CrawlSpider):
name = 'qsbkauto1'
allowed_domains = ['qiushibaike.com']
start_urls = ['http://www.qiushibaike.com/']
rules = (
Rule(LinkExtractor(allow=r'page/\d*/?s=\d*'), follow=True),
Rule(LinkExtractor(allow=(r'article/.*')), callback='parse_item',follow=True),
)
def parse_item(self, response):
item = QSBKAutoItem()
item["content"] = response.xpath("//div[@class='content']/text()").extract()[0]
# item["link"] = response.xpath("//link[@rel='canonical']/@href").extract()[0]
item["link"] = response.url
content = "内容:" + item["content"]
print(content.decode("utf-8"))
link = "链接:" + item["link"]
print(link.decode("utf-8"))
print("*************************************************************")
yield item