Pytorch-中文文本分类

1. 爬虫

JD.py

import requests
from urllib.parse import quote
from urllib.parse import urlencode
from lxml import etree
import logging
import json
import time
 
class JDSpider:
    # 爬虫实现类：传入商品类别（如手机、电脑），构造实例。然后调用getData爬取数据
    def __init__(self, categlory):
        self.startUrl = "https://search.jd.com/Search?keyword=%s&enc=utf-8" % (quote(categlory))  # jD起始搜索页面
        self.commentBaseUrl = "https://club.jd.com/comment/productPageComments.action?"
        self.headers = {
            "User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
        }
        self.productsId = self.getId()
        self.comtype = {0: "nagetive", 1: "medium