python3----scrapy(笔记)

import scrapy
import sys
# import io
# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18303')
from scrapy.selector import Selector, HtmlXPathSelector
class ChoutiSpider(scrapy.Spider):
name = 'chouti'
# allowed_domains = ['chouti.com']
start_urls = ['http://dig.chouti.com/'] def parse(self, response):
# print(response.text)
# content = str(response.body, encoding='utf-8')
# print(content)
# hxs = Selector(response=response).xpath('//a').extract()
# for i in hxs:
# print(i)
# hxs = Selector(response=response).xpath('//div[@id="content-list"]/div[@class="item"]').extract()
# for i in hxs:
# print(i)
hxs = Selector(response=response).xpath('//div[@id="content-list"]/div[@class="item"]') # 标签对像列表
for obj in hxs:
a = obj.xpath('.//a[@class="show-content color-chag"]/text()').extract_first()
print(a.strip()) '''
// 表示子孙中
.// 当前对像的子孙中
/ 儿子
/div 儿子中的div标签
/div[@id="i1" 儿子中的div标签且id=i1
obj.extract() 列表中的每一个对象转换成字符串 =>[]
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
//div/text() 获取某个标签的文本