python异步aiohttp爬虫 - 异步爬取链家数据

import requests

from lxml import etree

import asyncio

import aiohttp

import pandas

import re

import math

import time



loction_info = '''    1→杭州

    2→武汉

    3→北京

    按ENTER确认：'''

loction_select = input(loction_info)

loction_dic = {'1': 'hz',

               '2': 'wh',

               '3': 'bj'}

city_url = 'https://{}.lianjia.com/ershoufang/'.format(loction_dic[loction_select])

down = input('请输入价格下限（万）:')

up = input('请输入价格上限（万）:')



inter_list = [(int(down), int(up))]





def half_inter(inter):

    lower = inter[0]

    upper = inter[1]

    delta = int((upper - lower) / 2)

    inter_list.remove(inter)

    print('已经缩小价格区间', inter)

    inter_list.append((lower, lower + delta))

    inter_list.append((lower + delta, upper))





pagenum = {}





def get_num(inter):

    url = city_url + 'bp{}ep{}/'.format(inter[0], inter[1])

    r = requests.get(url).text

    print(r)

    num = int(etree.HTML(r).xpath("//h2[@class='total fl']/span/text()")[0].strip())

    pagenum[(inter[0], inter[1])] = num

    return num





totalnum = get_num(inter_list[0])



judge = True

while judge:

    a = [get_num(x) > 3000 for x in inter_list]

    if True in a:

        judge = True

    else:

        judge = False

    for i in inter_list:

        if get_num(i) > 3000:

            half_inter(i)

print('价格区间缩小完毕！')



url_lst = []

url_lst_failed = []

url_lst_successed = []

url_lst_duplicated = []



for i in inter_list:

    totalpage = math.ceil(pagenum[i] / 30)

    for j in range(1, totalpage + 1):

        url = city_url + 'pg{}bp{}ep{}/'.format(j, i[0], i[1])

        url_lst.append(url)

print('url列表获取完毕！')



info_lst = []





async def get_info(url):

    async with aiohttp.ClientSession() as session:

        async with session.get(url, timeout=5) as resp:

            if resp.status != 200:

                url_lst_failed.append(url)

            else:

                url_lst_successed.append(url)

            r = await resp.text()

            nodelist = etree.HTML(r).xpath("//ul[@class='sellListContent']/li")

            # print('-------------------------------------------------------------')

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url),len(url_lst)))

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url), len(url_lst)))

            # print('开始抓取第{}个页面的数据,共计{}个页面'.format(url_lst.index(url), len(url_lst)))

            # print('-------------------------------------------------------------')

            info_dic = {}

            index = 1

            print('开始抓取{}'.format(resp.url))

            print('开始抓取{}'.format(resp.url))

            print('开始抓取{}'.format(resp.url))

            for node in nodelist:

                try:

                    info_dic['title'] = node.xpath(".//div[@class='title']/a/text()")[0]

                except:

                    info_dic['title'] = '/'

                try:

                    info_dic['href'] = node.xpath(".//div[@class='title']/a/@href")[0]

                except:

                    info_dic['href'] = '/'

                try:

                    info_dic['xiaoqu'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[0]

                except:

                    info_dic['xiaoqu'] = '/'

                try:

                    info_dic['huxing'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[1]

                except:

                    info_dic['huxing'] = '/'

                try:

                    info_dic['area'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[2]

                except:

                    info_dic['area'] = '/'

                try:

                    info_dic['chaoxiang'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[3]

                except:

                    info_dic['chaoxiang'] = '/'

                try:

                    info_dic['zhuangxiu'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[4]

                except:

                    info_dic['zhuangxiu'] = '/'

                try:

                    info_dic['dianti'] = \

                    node.xpath(".//div[@class='houseInfo']")[0].xpath('string(.)').replace(' ', '').split('|')[5]

                except:

                    info_dic['dianti'] = '/'

                try:

                    info_dic['louceng'] = re.findall('\((.*)\)', node.xpath(".//div[@class='positionInfo']/text()")[0])

                except:

                    info_dic['louceng'] = '/'

                try:

                    info_dic['nianxian'] = re.findall('\)(.*?)年', node.xpath(".//div[@class='positionInfo']/text()")[0])

                except:

                    info_dic['nianxian'] = '/'

                try:

                    info_dic['guanzhu'] = ''.join(re.findall('[0-9]', node.xpath(".//div[@class='followInfo']/text()")[

                        0].replace(' ', '').split('/')[0]))

                except:

                    info_dic['guanzhu'] = '/'

                try:

                    info_dic['daikan'] = ''.join(re.findall('[0-9]',

                                                            node.xpath(".//div[@class='followInfo']/text()")[0].replace(

                                                                ' ', '').split('/')[1]))

                except:

                    info_dic['daikan'] = '/'

                try:

                    info_dic['fabu'] = node.xpath(".//div[@class='followInfo']/text()")[0].replace(' ', '').split('/')[

                        2]

                except:

                    info_dic['fabu'] = '/'

                try:

                    info_dic['totalprice'] = node.xpath(".//div[@class='totalPrice']/span/text()")[0]

                except:

                    info_dic['totalprice'] = '/'

                try:

                    info_dic['unitprice'] = node.xpath(".//div[@class='unitPrice']/span/text()")[0].replace('单价', '')

                except:

                    info_dic['unitprice'] = '/'

                if True in [info_dic['href'] in dic.values() for dic in info_lst]:

                    url_lst_duplicated.append(info_dic)

                else:

                    info_lst.append(info_dic)

                print('第{}条:    {}→房屋信息抓取完毕！'.format(index, info_dic['title']))

                index += 1

                info_dic = {}





start = time.time()



# 首次抓取url_lst中的信息，部分url没有对其发起请求，不知道为什么

tasks = [asyncio.ensure_future(get_info(url)) for url in url_lst]

loop = asyncio.get_event_loop()

loop.run_until_complete(asyncio.wait(tasks))



# 将没有发起请求的url放入一个列表，对其进行循环抓取，直到所有url都被发起请求

url_lst_unrequested = []

for url in url_lst:

    if url not in url_lst_successed or url_lst_failed:

        url_lst_unrequested.append(url)

while len(url_lst_unrequested) > 0:

    tasks_unrequested = [asyncio.ensure_future(get_info(url)) for url in url_lst_unrequested]

    loop.run_until_complete(asyncio.wait(tasks_unrequested))

    url_lst_unrequested = []

    for url in url_lst:

        if url not in url_lst_successed:

            url_lst_unrequested.append(url)

end = time.time()

print('当前价格区间段内共有{}套二手房源\(包含{}条重复房源\),实际获得{}条房源信息。'.format(totalnum, len(url_lst_duplicated), len(info_lst)))

print('总共耗时{}秒'.format(end - start))



df = pandas.DataFrame(info_lst)

df.to_csv("ljwh.csv", encoding='gbk')