python爬蟲爬取人人車（二手車）、利用padas、matplotlib生成圖表，將信息打成csv格式

該程序主要為了抓取人人車賣車信息，包括車系、車型號、購車日期、賣車價格、行駛路程、首付價格等等信息。話不多說直接代碼。

入庫之后將Mongodb里的信息導出成Excel語句

mongoexport -d myDB -c user -f _id,name,password,adress --csv -o ./user.csv

-d 標示 數據庫
-c 標示 數據表
-f 需要提取的field用逗號分隔
-o 輸出路徑

車系py文件

# -*- coding: utf-8 -*-
import re
from urllib.request import urlopen
from scrapy.http import Request
# from urllib.request import Request
from bs4 import BeautifulSoup
from lxml import etree
import pymongo
import scrapy
from scrapy.selector import HtmlXPathSelector
client = pymongo.MongoClient(host="127.0.0.1")
db = client.renrenche
collection = db.Carclass          #表名classification


import redis        #導入redis數據庫
r = redis.Redis(host='127.0.0.1', port=6379, db=0)

class renrencheSpider(scrapy.Spider):
    name = "Carinfo1"
    allowed_domains = ["renrenche.com"]   #允許訪問的域
    start_urls = [
        "https://www.renrenche.com/bj/ershouche/"
    ]

    #每爬完一個網頁會回調parse方法
    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        hx = hxs.select('//div[@class="brand-more-content"]/div[@class="brand-section brand-section-1"]/p[@class="bl"]/span[@class="bn"]/a')
        for secItem in hx:
            url = secItem.select("@href").extract()
            c = "https://www.renrenche.com"+url[0]
            name = secItem.select("text()").extract()
            classid =self.insertMongo(name,None)
            print(c)
            print(name)
            request = Request(c,callback=lambda response,pid=str(classid):self.parse_subclass(response,pid))
            yield request
    def parse_subclass(self, response,pid):
        # print(response.body.decode('utf-8'))
        hxs = HtmlXPathSelector(response)
        hx = hxs.select('//ul[@id="filter_series"]/li[@class=""]/a')
        for secItem in hx:
            urls = secItem.select("@href").extract()
            url = "https://www.renrenche.com" + urls[0]
            name = secItem.select("text()").extract()
            print(url)
            print(name)
            classid = self.insertMongo(name,pid)
            self.pushRedis(classid,url,pid)

    def insertMongo(self,classname,pid):
        classid = collection.insert({'classname':classname,'pid':pid})
        return classid
    def pushRedis(self,classid,url,pid,):
        carurl = '%s,%s,%s' %(classid,url,pid)
        r.lpush('carurl',carurl)

　　賣車各種信息py文件

# -*- coding: utf-8 -*-
import re
from urllib.request import urlopen
from scrapy.http import Request
import pymongo
import scrapy
from time import sleep
from scrapy.selector import HtmlXPathSelector

client = pymongo.MongoClient(host="127.0.0.1")
db = client.renrenche
collection = db.Carinfo

import redis  # 導入redis數據庫

r = redis.Redis(host='127.0.0.1', port=6379, db=0)




class renrencheSpider(scrapy.Spider):
    name = "Carinfo2"
    allowed_domains = ["renrenche.com"]
    dict = {}
    start_urls = []

    def __init__(self):  # 定義一個方法

        a = r.lrange('carurl', 0, -1)
        for item in a:
            novelurl = bytes.decode(item)
            arr = novelurl.split(',')  # 分割字符串
            renrencheSpider.start_urls.append(arr[1])
            pid = arr[0]
            url = arr[1]
            self.dict[url] = {"pid":pid,"num":0}


    def parse(self, response):

        classInfo = self.dict[response.url]
        pid = classInfo['pid']
        num = classInfo['num']
        # print(self.dict)
        if num>3:
            return None
        hxs = HtmlXPathSelector(response)
        hx = hxs.select('//ul[@class="row-fluid list-row js-car-list"]')
        s=""
        for secItem in hx:
            hx1 = secItem.select('//li[@class="span6 list-item car-item"]/a[@rrc-event-param="search"]/h3')
            name = hx1.select("text()").extract()
            a = "型號："+name[0]
            # self.insertMongo(classname=a)
            s +=a+"\n"
            # classid = collection.insert({'carinfo': a, 'pid': pid})
            # print(a)
        for secItem in hx:
            hx2 = secItem.select('//div[@class="mileage"]/span[@class="basic"]')
            name = hx2.select("text()").extract()
            b = "購車年份/公里數："+name[0]+"/"+name[1]
            # self.insertMongo(classname1=b)
            s +=b+"\n"
            # print(b)
        for secItem in hx:
            hx3 = secItem.select('//div[@class="tags-box"]/div[@class="price"]')
            name = hx3.select("text()").extract()
            c = str(name[0])
            c = c.strip()

            c = "賣車價格："+c+"萬"
            # self.insertMongo(classname2=c)
            s +=c+"\n"
            # print(c)
        for secItem in hx:
            hx4 = secItem.select('//div[@class="down-payment"]/div[@class="m-l"]')
            name = hx4.select("text()").extract()
            d = "首付："+name[0]+"萬"
            # self.insertMongo(classname3=d,pid=pid)
            s +=d+"\n"
            # print(d)
        # print(s)

        arr = s.split('\n')
        print(arr[0])
        classid = self.insertMongo(arr[0],arr[1],arr[2],arr[3],pid)
        # classid = self.insertMongo(s, pid)


    def insertMongo(self, classname,classname1,classname2,classname3, pid):
        classid = collection.insert({'classname': classname,'classname1':classname1,'classname2':classname2,'classname3':classname3, 'pid': pid})
        return classid
    #     r.lpush('novelnameurl', novelnameurl)