我是Scrapy的新手,我真的只是迷失了如何在一个区块中返回多个项目。
基本上,我得到一个HTML标签,其引用包含文本,作者姓名和有关该引用的一些标签的嵌套标签。
这里的代码只返回一个引用,就是这样。它不会使用循环返回其余部分。我一直在网上搜索几个小时,我只是没希望我没有得到它。到目前为止,这是我的代码:
Spider.py
import scrapy
from scrapy.loader import ItemLoader
from first_spider.items import FirstSpiderItem
class QuotesSpider(scrapy.Spider):
name = 'quotes'
allowed_domains = ['quotes.toscrape.com']
start_urls = ['http://quotes.toscrape.com/']
def parse(self, response):
l = ItemLoader(item = FirstSpiderItem(), response=response)
quotes = response.xpath("//*[@class='quote']")
for quote in quotes:
text = quote.xpath(".//span[@class='text']/text()").extract_first()
author = quote.xpath(".//small[@class='author']/text()").extract_first()
tags = quote.xpath(".//meta[@class='keywords']/@content").extract_first()
# removes quotation marks from the text
for c in ['“', '”']:
if c in text:
text = text.replace(c, "")
l.add_value('text', text)
l.add_value('author', author)
l.add_value('tags', tags)
return l.load_item()
next_page_path =
response.xpath(".//li[@class='next']/a/@href").extract_first()
next_page_url = response.urljoin(next_page_path)
yield scrapy.Request(next_page_url)
Items.py
import scrapy
class FirstSpiderItem(scrapy.Item):
text = scrapy.Field()
author = scrapy.Field()
tags = scrapy.Field()
这是我要抓的页面:
答案 0 :(得分:4)
我也在寻找同样问题的解决方案。以下是我找到的解决方案:
def parse(self, response):
for selector in response.xpath("//*[@class='quote']"):
l = ItemLoader(item=FirstSpiderItem(), selector=selector)
l.add_xpath('text', './/span[@class="text"]/text()')
l.add_xpath('author', '//small[@class="author"]/text()')
l.add_xpath('tags', './/meta[@class="keywords"]/@content')
yield l.load_item()
next_page = response.xpath(".//li[@class='next']/a/@href").extract_first()
if next_page is not None:
yield response.follow(next_page, callback=self.parse)
要从文字中删除引号,您可以在 items.py 中使用输出处理器。
from scrapy.loader.processors import MapCompose
def replace_quotes(text):
for c in ['“', '”']:
if c in text:
text = text.replace(c, "")
return text
class FirstSpiderItem(scrapy.Item):
text = scrapy.Field()
author = scrapy.Field()
tags = scrapy.Field(output_processor=MapCompose(replace_quotes))
请告诉我这是否有帮助。
答案 1 :(得分:1)
试一试。它将为您提供您想要抓取的所有数据。
import scrapy
class QuotesSpider(scrapy.Spider):
name = 'quotes'
start_urls = ['http://quotes.toscrape.com/']
def parse(self, response):
for quote in response.xpath("//*[@class='quote']"):
text = quote.xpath(".//span[@class='text']/text()").extract_first()
author = quote.xpath(".//small[@class='author']/text()").extract_first()
tags = quote.xpath(".//meta[@class='keywords']/@content").extract_first()
yield {"Text":text,"Author":author,"Tags":tags}
next_page = response.xpath(".//li[@class='next']/a/@href").extract_first()
if next_page:
next_page_url = response.urljoin(next_page)
yield scrapy.Request(next_page_url)