使用爬虫框架Scrapy爬取get请求中的数据 及其详情页内容
"""
直接请求get网页数据,不涉及使用items和pipelines
目前不涉及翻页
"""
class XxxSpider(scrapy.Spider):
...
start_urls = ['需要获取列表数据的链接']
"""
获取页面元素列表内容
"""
def parse(self, response):
if response.status == 200 and len(response.text) > 10:
titles = response.xpath('xpath解析语句').extract()
urls = response.xpath('xpath解析语句').extract()
for i in range(0,len(titles)):
url = urls[i]
title = titles[i]
print(url, title)
yield scrapy.Request(url=url, callback=self.html)
"""
获取url详情页中的数据
"""
def html(self.response):
if response.status == 200 and len(response.text) > 10:
content = response.xpath('xpath解析语句').extract()
print(content)