Python爬虫学习日志（10）

编写爬虫

1. 功能描述

• 目标：获取上交所和深交所所有股票的名称和交易信息。
• 输出：保存到本地文件中。

候选数据网站的选择

• 选取原则：股票信息静态存在于HTML页面中，非js代码生成，没有Robots协议限制。
• 选取方法：浏览器F12，源代码查看等。
• 选取心态：不要纠结于某个网站，多找信息源尝试。
  此处选取的网站（2019/12/3可用）：东方财富网和老虎社区
• 股票代码查询 ：http://quote.eastmoney.com/stock_list.html
• 个股信息 ：https://www.laohu8.com/quotes

2. 技术路线：requests-re

源代码

import requests
from bs4 import BeautifulSoup
import traceback
import re

def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def getStockList(lst, stockURL):
    html = getHTMLText(stockURL)
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])#正则表达式，以s开头，中间是h或z,后面有6个数字
        except:
            continue

def getStockInfo(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div', attrs= {'class':'stock-bets'})

            name = stockInfo.find_all(attrs = {'class':'bets-name'})[0]
            infoDict.update({'股票名称':name.text.split()[0]})#split空格分割

            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val#添加到字典中

            with open(fpath, 'a', encoding= 'utf-8') as f:
                f.write(str(infoDict) + '\n')

        except:
            traceback.print_exc()#获得错误信息
            continue

    return ""

def main():
    stock_list_url = 'http://quote.eastmoney.com/stock_list.html'
    stock_info_url = 'https://www.laohu8.com/quotes'
    output_file = 'E://BaiduStockInfo.txt'
    slist = []
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)

print(main)

输出结果：

网站问题暂未解决，无结果。

代码优化

def getHTMLText(url, code= 'utf-8'):#code默认utf-8编码
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        # r.encoding = r.apparent_encoding
        r.encoding = code #直接赋值编码类型，提高速度
        return r.text
    except:
        return ""

def getStockInfo(lst, stockURL, fpath):
    count = 0
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div', attrs= {'class':'stock-bets'})

            name = stockInfo.find_all(attrs = {'class':'bets-name'})[0]
            infoDict.update({'股票名称':name.text.split()[0]})#split空格分割

            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val#添加到字典中

            with open(fpath, 'a', encoding= 'utf-8') as f:
                f.write(str(infoDict) + '\n')
                count = count + 1
                #打印当前进度的百分比
                # \r: 转义符，将打印字符串最后的光标提到字符串的头部，下次打印时会覆盖上次的信息，实现不换行的显示。.2f: 浮点型，两位小数
                print('\r当前速度：{：.2f}%'.format(count*100/len(lst)),end='')
        except:
            traceback.print_exc()#获得错误信息
            continue

    return ""

3. 技术路线：Scrapy爬虫框架

步骤

1. 建立工程和Spider模板
2. 编写Spider
3. 编写ITEM Pipeline

步骤1

• >scrapy startproject BaiduStocks
• >cd BaiduStocks
• >scrapy genspider stock baidu.com
• 进一步修改spiders/stocks.py文件

步骤2

• 配置stocks.py文件
• 修改对返回页面的处理
• 修改对新增URL爬取请求的处理

步骤3

• 配置pipelines.py文件
• 定义对爬取项（Scraped Item）的处理类
• 配置ITEM_PIPELINES选项

执行Scrapy爬虫

• >scrapy crawl stocks

源代码

stocks.py

# -*- coding: utf-8 -*-
import scrapy
import re

class StockSpider(scrapy.Spider):
    name = 'stocks'
    start_urls = ['http://quote.eastmoney.com/stockslist.html']

    def parse(self, response):
        for href in response.css('a::attr(href)').extract():
            try:
                stock = re.findall(r"[s][hz]\d{6}", href)[0]
                url = 'https://gupiao.baidu.com/stock/' + stock + '.html'
                yield scrapy.Reauest(url, callback= self.parse_stock)
            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][0:-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://docs.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', 'w')

    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
将该部分进行以下修改

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}

输出结果：

网站问题暂未解决，无结果。

代码优化

参考相关文档进行侧重修改，提高性能。

更多

Scrapy爬虫的功能和特点：

• 持续爬取
• 商业服务
• 高可靠性

4. 存在的问题

• 视频中爬取股票的实例网站（百度股票和东方财富网），现在已不可用或存在非静态代码，后续修改。
• 此实例为单线程爬虫，运行较慢，请耐心等待。

视频学习部分OVER！