数据采集技术第三次作业

作业①

1）爬取中国气象网的所有图片实验

(1)单线程
代码部分

import re
import requests
from multiprocessing.dummy import Pool
from bs4 import BeautifulSoup
import os
import time
if not os.path.exists('./image1'):
    os.mkdir('./image1')
headers = {
        "User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre"
        }
url = "http://www.weather.com.cn/"
data_url_list = []
start_time = time.time()
response = requests.get(url = url,headers =headers)
page_text = response.text
soup = BeautifulSoup(page_text,"lxml")
img_list = soup.select("img")
for img in img_list:
    detail_url = img["src"]
    data_url_list.append(detail_url)
# print(data_url_list)
for data_url in data_url_list:
    data = requests.get(url=data_url,headers=headers).content
    name = data_url.split('/')[-1]
    path_name = './image1/' + name
    print("正在下载"+name)
    with open(path_name,"wb") as fp:
        fp.write(data)
        print(name+"下载完成")
end_time = time.time()
print("所用时间为"+str(end_time-start_time)+"秒")

结果如下

(2)多线程
代码部分

import time
import os
from bs4 import BeautifulSoup
import requests
from multiprocessing.dummy import Pool
headers = {
        "User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre"
        }
if not os.path.exists('./image2'):
    os.mkdir('./image2')
url = "http://www.weather.com.cn/"
start_time = time.time()
page_text = requests.get(url = url,headers=headers).text
soup = BeautifulSoup(page_text,"lxml")
img_list = soup.select("img")
date_url_list = []
for img in img_list:
    data_url = img["src"]
    date_url_list.append(data_url)

def save_image(image_url):
    data = requests.get(url=url,headers=headers).content
    name = image_url.split('/')[-1]
    print("正在下载",name)
    path_name = './image2/' + name
    with open(path_name,"wb") as fp:
        fp.write(data)
    print(name,"下载成功")
pool = Pool(5)
pool.map(save_image,date_url_list)
pool.close()
pool.join()
end_time = time.time()
print("一共耗时"+str(end_time-start_time))

结果如下

2)心得体会

因为书上代码比较繁琐，看起来有点累，就自己打了一下。通过实验，可以看出多线程爬取图片所用的时间更少，可以为相关阻塞的操作单独开启线程，阻塞操作就可以异步执行。这里我使用了线程池，对比了一下其它同学的实验结果，好像耗时要长不少，不过我们可以降低系统对进程或者线程创建和销毁的一个频率，从而很好的降低系统的开销。弊端就是这样做的话线程池里面的线程数量有限。（我是设置了线程池的大小为5个）

作业②

1）使用scrapy框架复现作业①实验

代码部分
img_download.py

import scrapy
import os
from ..items import ImgDownloadproItem
class ImgDownloadSpider(scrapy.Spider):
    name = 'img_download'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://www.weather.com.cn/']
    if not os.path.exists('./images'):
        os.mkdir('./images')
    def parse(self, response):
        src_list = response.xpath('//img/@src').extract()  #对于一个列表使用extract()方法,得到的也是一个列表  这样我们就得到了我们想要的url
        for src in src_list:
            item = ImgDownloadproItem()   #实例化item对象
            item['src'] = src             
            yield item        #将之提交给管道，然后进行持久化存储

items.py

import scrapy


class ImgDownloadproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    src = scrapy.Field()

    pass

settings.py

BOT_NAME = 'img_downloadPro'

SPIDER_MODULES = ['img_downloadPro.spiders']
NEWSPIDER_MODULE = 'img_downloadPro.spiders'
LOG_LEVEL = 'ERROR'  #这样设置就可以只看到提示错误的日志信息了


USER_AGENT = 'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre' #UA伪装

# Obey robots.txt rules
ROBOTSTXT_OBEY = False  #爬取数据的时候君子协议可以设置成False


ITEM_PIPELINES = {
   'img_downloadPro.pipelines.ImgDownloadproPipeline': 300,
}

pipelines.py

from itemadapter import ItemAdapter
import requests

class ImgDownloadproPipeline:
    def process_item(self, item, spider):
        src = item["src"]
        name = src.split('/')[-1]
        data = requests.get(url=src).content
        path_name = './images/'+name
        with open(path_name,"wb") as fp:
            print("正在下载",name)
            fp.write(data)
            print("下载完成",name)
        fp.close()
        return item

结果展示

2)心得体会

本次实验花费了我不少时间，可能是ddl到了，太慌了没打出来。。。通过本次实验我对Scrapy框架熟悉了很多，以及在srcapy中使用xpath方法的返回值是选择器，如果要提取我们想要的信息，要再后面加一个extract()方法。本次实验之后，我对五大核心组件在框架中所扮演的角色有了进一步的了解，通过编程实践，我也逐渐熟悉了各自的作用。听说ImagesPipeline是专门实现对图片的爬取，本次实验由于时间紧迫，下次再作尝试。

作业③

1）使用scrapy框架爬取股票相关信息

代码部分
Gupiao.py

import scrapy
import re
import json
from ..items import GupiaoproItem
class GupiaoSpider(scrapy.Spider):
    name = 'Gupiao'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://75.push2.eastmoney.com/api/qt/clist/get?&pn=1&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&fid=f3&fs=m:1+t:2,m:1+t:23&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152&_=1602901412583%20Request%20Method:%20GET']

    def parse(self, response):
        data1 = json.loads(response.text)
        data = data1["data"]
        diff = data["diff"]   #借鉴前面优秀同学的博客，josn.loads比上次自己用正则去匹配方便很多
                              #diff的值就是一个大列表，里面是小字典
        for i in range(len(diff)):
            item = GupiaoproItem()
            item["count"]=str(i)
            item["code"]=str(diff[i]["f12"])
            item["name"]=str(diff[i]["f14"])
            item["new_price"]=str(diff[i]["f2"])
            item["zhangdiefu"]=str(diff[i]["f3"])
            item["zhangdieer"]=str(diff[i]["f4"])
            item["com_num"]=str(diff[i]["f5"])
            item["com_price"]=str(diff[i]["f6"])
            item["zhengfu"]=str(diff[i]["f7"])
            item["top"]=str(diff[i]["f15"])
            item["bottom"]=str(diff[i]["f16"])
            item["today"]=str(diff[i]["f17"])
            item["yesterday"]=str(diff[i]["f18"])
            yield item

items.py

class GupiaoproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    count = scrapy.Field()
    code = scrapy.Field()
    name = scrapy.Field()
    new_price = scrapy.Field()
    zhangdiefu = scrapy.Field()
    zhangdieer = scrapy.Field()
    com_num = scrapy.Field()
    com_price = scrapy.Field()
    zhengfu = scrapy.Field()
    top = scrapy.Field()
    bottom = scrapy.Field()
    today = scrapy.Field()
    yesterday = scrapy.Field()
    pass

settings.py

LOG_LEVEL = 'ERROR'  #这样设置就可以只看到提示错误的日志信息了


USER_AGENT = 'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre' #UA伪装

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
ITEM_PIPELINES = {
   'GupiaoPro.pipelines.GupiaoproPipeline': 300,
}

pipelines.py

from itemadapter import ItemAdapter   
   
    
    
class GupiaoproPipeline:

    fp = None
    #重写父类的一个方法：该方法只在开始爬虫的时候被调用一次，避免多次打开文件
    def open_spider(self,spider):
        print('开始爬虫......')
        self.fp = open('./gupiao.txt','w',encoding='utf-8')
        self.fp.write("序号" + "        股票代码" + "    股票名称  " + " 最新报价  " + " 涨跌幅  " + "  涨跌额  " +"      成交量   " + "       成交额         " + "  振幅   " + "最高   " + "最低   " + "今开    "+ " 昨收  " + "\n")


    def process_item(self, item, spider):
        #设置对齐的格式
        tplt = "{0:^2}\t{1:^1}\t{2:{13}^4}\t{3:^5}\t{4:^6}\t{5:^6}\t{6:^6}\t{7:^10}\t{8:^10}\t{9:^10}\t{10:^10}\t{11:^10}\t{12:^10}"
        

        self.fp.write(
                tplt.format(item["count"], item["code"], item["name"], item['new_price'], item['zhangdiefu'],
                            item['zhangdieer'], item['com_num'],item['com_price'],item['zhengfu'],
                            item['top'],item['bottom'],item['today'],item['yesterday'],chr(12288)))
        self.fp.write('\n')
        
        return item
    
    def close_spider(self,spider):  #同样只要定义一次
        print('结束爬虫！')
        self.fp.close()

结果展示

2）心得体会

这次的实验和上次差不多，不过在参考了同学的一些代码后，发现用json.loads()方法要方便很多，不用像正则表达式那样看地眼花缭乱，还有就是在pipeline.py的编写时，可以把打开文件和关闭文件的方法写在外面，这样避免了不必要的资源浪费。因为process_item(self, item, spider)会根据所接收到的item对象执行多次，还有就是settings.py的设置，LOG_LEVEL = 'ERROR'能够只显示代码的错误信息，方便我们进行代码的调试。经过本次实验，我可以更加熟练地运用scrapy框架。