1 import scrapy 2 import sys 3 # import io 4 # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding=‘gb18303‘) 5 from scrapy.selector import Selector, HtmlXPathSelector 6 class ChoutiSpider(scrapy.Spider): 7 name = ‘chouti‘ 8 # allowed_domains = [‘chouti.com‘] 9 start_urls = [‘http://dig.chouti.com/‘] 10 11 def parse(self, response): 12 # print(response.text) 13 # content = str(response.body, encoding=‘utf-8‘) 14 # print(content) 15 # hxs = Selector(response=response).xpath(‘//a‘).extract() 16 # for i in hxs: 17 # print(i) 18 # hxs = Selector(response=response).xpath(‘//div[@id="content-list"]/div[@class="item"]‘).extract() 19 # for i in hxs: 20 # print(i) 21 hxs = Selector(response=response).xpath(‘//div[@id="content-list"]/div[@class="item"]‘) # 标签对像列表 22 for obj in hxs: 23 a = obj.xpath(‘.//a[@class="show-content color-chag"]/text()‘).extract_first() 24 print(a.strip()) 25 26 ‘‘‘ 27 // 表示子孙中 28 .// 当前对像的子孙中 29 / 儿子 30 /div 儿子中的div标签 31 /div[@id="i1" 儿子中的div标签且id=i1 32 obj.extract() 列表中的每一个对象转换成字符串 =>[] 33 obj.extract_first() 列表中的每一个对象转换成字符串=>列表第一个元素 34 //div/text() 获取某个标签的文本
