第三次作业

作业1

1）、实验内容：指定一个网站，爬取这个网站中的所有的所有图片，例如中国气象网（http://www.weather.com.cn）。分别使用单线程和多线程的方式爬取

这个代码在书上有，我们只是做了一个复现。

单线程代码如下：

from bs4 import BeautifulSoup
from bs4 import UnicodeDammit
import urllib.request
import scrapy

def imageSpider(start_url):
    try:
        urls=[]
        req = urllib.request.Request(start_url,headers=headers)
        data=urllib.request.urlopen(req)
        data=data.read()
        dammit=UnicodeDammit(data,["utf-8","gbk"])
        data=dammit.unicode_markup
        soup=BeautifulSoup(data,"lxml")
        images=soup.select("img")
        for image in images:
            try:
                src=image["src"]
                url=urllib.request.urljoin(start_url,src)
                if url not in urls:
                    urls.append(url)
                    print(url)
                    download(url)
            except Exception as err:
                print(err)
    except Exception as err:
        print(err)

def download(url):
    global count
    try:
        count=count+1
        if(url[len(url)-4]=="."):
            ext=url[len(url)-4:]
        else:
            ext=""
        req=urllib.request.Request(url,headers=headers)
        data=urllib.request.urlopen(req,timeout=100)
        data=data.read()
        fobj=open(r"images/"+str(count)+ext,"wb")
        fobj.write(data)
        fobj.close()
        print("downloaded"+str(count)+ext)
    except Exception as err:
        print(err)

start_url="http://www.weather.com.cn/weather/101280601.shtml"

headers={"User-Agent":"Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre"}
count=0
imageSpider(start_url)

单线程结果如下：

多线程代码如下：

from bs4 import BeautifulSoup
from bs4 import UnicodeDammit
import urllib.request
import threading

def imageSpider(start_url):
    global threads
    global count
    try:
        urls=[]
        req = urllib.request.Request(start_url,headers=headers)
        data=urllib.request.urlopen(req)
        data=data.read()
        dammit=UnicodeDammit(data,["utf-8","gbk"])
        data=dammit.unicode_markup
        soup=BeautifulSoup(data,"lxml")
        images=soup.select("img")
        for image in images:
            try:
                src=image["src"]
                url=urllib.request.urljoin(start_url,src)
                if url not in urls:
                    print(url)
                    count=count+1
                    T=threading.Thread(target=download,args=(url,count))
                    T.setDaemon(False)
                    T.start()
                    threads.append(T)
            except Exception as err:
                print(err)
    except Exception as err:
        print(err)

def download(url,count):
    try:

        if(url[len(url)-4]=="."):
            ext=url[len(url)-4:]
        else:
            ext=""
        req=urllib.request.Request(url,headers=headers)
        data=urllib.request.urlopen(req,timeout=100)
        data=data.read()
        fobj=open(r"images1/"+str(count)+ext,"wb")
        fobj.write(data)
        fobj.close()
        print("downloaded"+str(count)+ext)
    except Exception as err:
        print(err)

start_url="http://www.weather.com.cn/weather/101280601.shtml"

headers={"User-Agent":"Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre"}
count=0
threads=[]
imageSpider(start_url)
for t in threads:
    t.join()
print("The End")

多线程结果如下：

2）、心得体会

这次实验是书上原封不动的实验的复现，通过对单线程和多线程的复现，我们了解到了如何利用线程更高效的爬取网站内容。

作业2

1）、实验内容：使用scrapy框架复现作业①。

scrapy各部分框架代码如下：

MySpider代码：

import scrapy
import re
from scrapy.http import Request
from ..items import ImgItem

class MySpider(scrapy.Spider):
    name = "MySpider"
    allowed_domains = ['weather.com.cn']
    start_urls=["http://www.weather.com.cn/weather/101280601.shtml"]

    def parse(self, response):
        try:
            data = response.body.decode()
            selector = scrapy.Selector(text=data)
            srcs = selector.xpath('//img/@src').extract()  
            for src in srcs:
                print(src)
                item = ImgItem()
                item['src'] = src
                yield item
        except Exception as err:
            print(err)

items的代码：

import scrapy
class ImgItem(scrapy.Item):
    # name = scrapy.Field()
    src = scrapy.Field()
    pass

pipelines的代码：

import urllib
from scrapy.pipelines.images import ImagesPipeline
class ImagePipeline:
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36"}
    count = 0
    def process_item(self, item, spider):
        try:
            self.count += 1
            src = item['src']
            if src[len(src) - 4] == ".":
                ext = src[len(src) - 4:]
            else:
                ext = ""
            req = urllib.request.Request(src, headers=self.headers)
            data = urllib.request.urlopen(req, timeout=100)
            data = data.read()
            fobj = open("E:\python\spider_work\demo\demo\images\" + str(self.count) + ext, "wb")
            fobj.write(data)
            fobj.close()
            print("downloaded "+str(self.count)+ext)
        except Exception as err:
            print(err)
        return item

settings的代码：

BOT_NAME = 'demo'

SPIDER_MODULES = ['demo.spiders']
NEWSPIDER_MODULE = 'demo.spiders'

ITEM_PIPELINES = {
    'demo.pipelines.ImagePipeline': 300,
}

ROBOTSTXT_OBEY = False

实验结果：

2）、心得体会

scrapy的框架其实就是将原来的爬虫代码按功能拆分成好几个部分，然后分别写在scrapy提供的各个文件下，这样便于实现大规模的爬虫程序，其实爬虫的内核没有什么变化，但是需要注意一些细节的变化，这样才能够爬出正确的结果。在这个实验中，用MySpider获得各个图片的url,再通过pipelines写下载保存的方法。

作业3

1）、实验内容：使用scrapy框架爬取股票相关信息。

各部分代码如下：

MySpider代码：

import scrapy
import json
from ..items import StockItem
class stockSpider(scrapy.Spider):
    name = 'stock'
    start_urls = ['http://49.push2.eastmoney.com/api/qt/clist/get?cb=jQuery11240918880626239239_1602070531441&pn=1&pz=20&po=1&np=3&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&_=1602070531442']
    def parse(self, response):
        jsons = response.text[41:][:-2]  # 将前后用不着的字符排除
        text_json = json.loads(jsons)
        for data in text_json['data']['diff']:
            item = StockItem()
            item["f12"] = data['f12']
            item["f14"] = data['f14']
            item["f2"] = data['f2']
            item["f3"] = data['f3']
            item["f4"] = data['f4']
            item["f5"] = data['f5']
            item["f6"] = data['f6']
            item["f7"] = data['f7']
            yield item
        print("完成")

items的代码：

import scrapy
class StockItem(scrapy.Item):
    f12 = scrapy.Field()
    f14 = scrapy.Field()
    f2 = scrapy.Field()
    f3 = scrapy.Field()
    f4 = scrapy.Field()
    f5 = scrapy.Field()
    f6 = scrapy.Field()
    f7 = scrapy.Field()
    pass

pipelines的代码：

class stockPipeline(object):
    count = 0
    print("序号	", "代码	", "名称	", "最新价（元）	 ", "涨跌幅 （%）	", "跌涨额（元）	", "成交量	", "成交额(元)	", "涨幅（%）	")
    def process_item(self, item, spider):
        self.count += 1
        print(str(self.count) + "	", item['f12'] + "	", item['f14'] + "	", str(item['f2']) + "	", str(item['f3']) + "%	",str(item['f4']) + "	", str(item['f5']) + "	", str(item['f6']) + "	", str(item['f7']) + "%")

        return item

settings的代码：

BOT_NAME = 'stock'
SPIDER_MODULES = ['stock.spiders']
NEWSPIDER_MODULE = 'stock.spiders'
ITEM_PIPELINES = {
    'stock.pipelines.stockPipeline': 300,
}

实验结果：

2）、心得体会

有了上一次爬取股票作业的基础，用scrapy复现就没有那么难，就是按各个部分拆分代码，MySpider用来爬取，pipelines用来按格式输出等等。