股票数据Scrapy爬虫（北理-嵩天）

视频和讲解，附链接

https://www.jianshu.com/p/be3024c86c4c

会出现403，触发反爬机制

解决方式：检测User-Agent，因此这里可以通过使用随机User-Agent来进行爬取。 

参考：https://blog.csdn.net/sinat_34073684/article/details/71433629

下面附上我的代码，以及运行结果

stocks.py

import scrapy
import re
import random

class StocksSpider(scrapy.Spider):
    user_agent_list = [ \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
    ]
    name = 'stocks'
    start_urls = ['http://quote.eastmoney.com/stocklist.html']

    def parse(self, response):
        ua = random.choice(self.user_agent_list)  # 随机抽取User-Agent
        headers = {
            'Accept-Encoding': 'gzip, deflate, sdch, br',
            'Accept-Language': 'zh-CN,zh;q=0.8',
            'Connection': 'keep-alive',
            'Referer': 'https://gupiao.baidu.com/',
            'User-Agent': ua
        }  # 构造请求头
        for href in response.css("a::attr(href)").extract():
            try:
                stock = re.findall(r"[s][hz]\d{6}", href)[0]
                url = "http://gupiao.baidu.com/stock/" + stock + ".html"
                yield scrapy.Request(url, callback=self.parse_stock,headers = headers)
            except:
                continue

    def parse_stock(self, response):
        infoDict = {}
        stockInfo = response.css(".stock-bets")
        name = stockInfo.css(".bets-name").extract()[0]
        keyList = stockInfo.css("dt").extract()
        valueList = stockInfo.css("dd").extract()
        for i in range(len(keyList)):
            key = re.findall(r'>.*</dt>', keyList[i])[0][1:-5]
            try:
                val = re.findall(r'\d+\.?.*</dd>', valueList[i])[0][1:-5]
            except:
                val = '--'
            infoDict[key] = val

        infoDict.update(
            {"股票名称": re.findall('\s.*\(', name)[0].split()[0] + \
                     re.findall("\>.*\<", name)[0][1:-1]})

        yield infoDict

pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html


class BaidustocksPipeline(object):
    def process_item(self, item, spider):
        return item
class BaidustocksInfoPipeline(object):
    def open_spider(self,spider):
        self.f = open("BaiduStockInfo.txt","a")

    def close_spider(self,spider):
        self.f.close

    def process_item(self,item,spider):
        try:
            line=str(dict(item))+'\n'
            self.f.write(line)
        except:
            pass

        return item

setting.py

ITEM_PIPELINES = {
   'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}

下面应该会多看参考手册，试着自己写写爬虫了，希望暑假剩下的一个月能更充实