scrapy--json(喜马拉雅Fm)(二)

学习了对数据的储存,感觉还不够深入,昨天开始对储存数据进行提取、整合和图像化显示。实例还是喜马拉雅Fm,算是对之前数据爬取之后的补充。

明确需要解决的问题

1,蕊希电台全部作品的进行储存       --scrapy爬取:作品id(trackid),作品名称(title),播放量playCount
2,储存的数据进行提取,整合              --pandas运用:提取出trackid,playCount;对播放量进行排序,找出最高播放量(palyCount)的作品
3.整合的数据图像化显示 　　　　    --matplotlib图像化,清楚的查看哪些作品最受欢迎:trackid作为x轴,播放量(playCount)作为y轴

三、给大家看下成果

3.1_蕊希电台所有作品数(369)

3.2_全部储存到mongoDB数据库

3.3_导出csv文件:mongoexport -d ruixi -c ruixi -f trackid,playc --csv -o Desktop\ruixi.csv

3.4_图像化显示

二、items.py,middlewares.py就不讲了,可以看我之前的博客;重点说一下其他3个文件

2.1_爬虫文件:spiders/ruixi.py

# -*- coding: utf-8 -*-
import scrapy
from Ruixi.items import RuixiItem
import json
from Ruixi.settings import USER_AGENT
import re

class RuixiSpider(scrapy.Spider):
    name = 'ruixi'
    allowed_domains = ['www.ximalaya.com']
    start_urls = ['https://www.ximalaya.com/revision/track/trackPageInfo?trackId=129503750']

    def parse(self, response):
        ruixi = RuixiItem()
        #使用json,提取需要文件
        ruixi['trackid'] = json.loads(response.body)['data']['trackInfo']['trackId']
        ruixi['title']   = json.loads(response.body)['data']['trackInfo']['title']
        ruixi['playc']   = json.loads(response.body)['data']['trackInfo']["playCount"]

        yield ruixi

        #对当前页面的trackid进行提取,生成新的url,跳转至下一链接,继续提取
        for each_item in json.loads(response.body)['data']["moreTracks"]:
            each_trackid = each_item['trackId']
            new_url = 'https://www.ximalaya.com/revision/track/trackPageInfo?trackId=' + str(each_trackid)
            yield scrapy.Request(new_url,callback=self.parse)

2.2_管道文件配置: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
import scrapy
import pymongo
from scrapy.item import Item
from scrapy.exceptions import DropItem
import codecs
import json
from openpyxl import Workbook

#储存之前,进行去重处理
class DuplterPipeline():
    def __init__(self):
        self.set = set()
    def process_item(self,item,spider):
        name = item['trackid']
        if name in self.set():
            raise DropItem('Dupelicate the items is%s' % item)

        self.set.add(name)
        return item

class RuixiPipeline(object):
    def process_item(self, item, spider):
        return item

#存储到mongodb中
class MongoDBPipeline(object):
    @classmethod
    def from_crawler(cls,crawler):
        cls.DB_URL = crawler.settings.get("MONGO_DB_URL",'mongodb://localhost:27017/')
        cls.DB_NAME = crawler.settings.get("MONGO_DB_NAME",'scrapy_data')
        return cls()

    def open_spider(self,spider):
        self.client = pymongo.MongoClient(self.DB_URL)
        self.db     = self.client[self.DB_NAME]

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

    def process_item(self,item,spider):
        collection = self.db[spider.name]
        post = dict(item) if isinstance(item,Item) else item
        collection.insert(post)

        return item

#储存至.Json文件
class JsonPipeline(object):
    def __init__(self):
        self.file = codecs.open('data_cn.json', 'wb', encoding='gb2312')

    def process_item(self, item, spider):
        line = json.dumps(dict(item)) + '\n'
        self.file.write(line.decode("unicode_escape"))
        return item

#储存至.xlsx文件
class XlsxPipeline(object):  # 设置工序一
    def __init__(self):
        self.wb = Workbook()
        self.ws = self.wb.active

    def process_item(self, item, spider):  # 工序具体内容
        line = [item['trackid'], item['title'], item['playc']]  # 把数据中每一项整理出来
        self.ws.append(line)  # 将数据以行的形式添加到xlsx中
        self.wb.save('ruixi.xlsx')  # 保存xlsx文件
        return item

2.3_设置文件:settings.py

MONGO_DB_URL = 'mongodb://localhost:27017/'
MONGO_DB_NAME = 'ruixi'

FEED_EXPORT_ENCODING = 'utf-8'

USER_AGENT =[       #设置浏览器的User_agent
    "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"
]

FEED_EXPORT_FIELDS = ['trackid','title','playc']

ROBOTSTXT_OBEY = False
CONCURRENT_REQUESTS = 10
DOWNLOAD_DELAY = 0.5
COOKIES_ENABLED = False
# Crawled (400) <GET https://www.cnblogs.com/eilinge/> (referer: None)
DEFAULT_REQUEST_HEADERS = 
{ 
'User-Agent': random.choice(USER_AGENT), 
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 
'Accept-Language': 'en', 
}

DOWNLOADER_MIDDLEWARES = 
{
    'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware':543,
    'Ruixi.middlewares.RuixiSpiderMiddleware': 144,
}

ITEM_PIPELINES = 
{
    'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware':1,
    'Ruixi.pipelines.DuplterPipeline': 290,
    'Ruixi.pipelines.MongoDBPipeline': 300,
    'Ruixi.pipelines.JsonPipeline':301,
    'Ruixi.pipelines.XlsxPipeline':302,
}

2.4_生成报表

#-*- coding:utf-8 -*-
import matplotlib as mpl
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import pdb

df = pd.read_csv("ruixi.csv")
df1= df.sort_values(by='playc',ascending=False)

df2 = df1.iloc[:10,:]

df2.plot(kind='bar',x='trackid',y='playc',alpha=0.6) 
plt.xlabel("trackId") 
plt.ylabel("playc") 
plt.title("ruixi") 
plt.show()