栏目抓取网站日kafka

#!/usr/bin/python3
#-*- coding:utf-8 -*-
"""
create 2018-02-27
author zl
desc:
    https://indianexpress.com#印度快报
files:
    indianexpress.py         #爬虫
    config.ini #配置文件
    max_main_interval  #脚本循环间隔
    network_timeout #超时
    proxy   #代理
dependent:
    configparser,bs4
usage:
    skip

"""

config.ini

[indianexpress]

max_main_interval=

network_timeout=

proxy=

indianexpress.py

#!/usr/bin/python3

#-*- coding:utf- -*-

"""

create --

author zl

desc:

    https://indianexpress.com#印度快报

files:

    indianexpress.py         #爬虫

    config.ini #配置文件

    max_main_interval  #脚本循环间隔

    network_timeout #超时

    proxy   #代理

dependent:

    configparser,bs4

usage:

    skip

"""

from pb_code import *

from bs4 import BeautifulSoup

import re

import time

def get_list(urls):

    for url in urls['url']:

        try:

            resp=fetch_get(False,url,network_timeout,proxy)

            if resp is not None:

                soup=BeautifulSoup(resp,'html.parser')

                news_list=soup.find_all('div',class_=urls['list_class'])

                for art in news_list:

                    timedate=art.find('div',class_='date').text

                    #print(timedate)

                    timepattern=re.compile('\w+ \d{1,2}, \d{4} \d{1,2}:\d{1,2}')

                    t1=timepattern.findall(timedate)

                    timestamp=int(time.mktime(time.strptime(t1[],"%B %d, %Y %H:%M")))+*2.5

                    if 'pm' in timedate:

                        timestamp=timestamp+*

                    if int(time.time())-timestamp<:

                        title=art.find('div',class_='title')

                        #print(title)

                        url=title.find('a')

                        art_json={

                            "publishtime":time.strftime("%Y-%m-%d %X",time.localtime(timestamp)),

                            "author":"",

                            "title":url.text,

                            "content":"",

                            "gathertime":time.strftime("%Y-%m-%d %X",time.localtime()),

                            "inserttime":"",

                            "url":url.attrs['href'],

                            "group_id":"",

                            "site_id":"",

                            "site_url":"",

                            "language":"EN"

                        }

                        get_page(urls['page_content_id'],art_json)

                    elif timestamp is not None:

                        break

        except Exception as e:

            print('get_list {} ,{}'.format(e,url))

        time.sleep(random.randint(,))

def get_page(tag_id,art_json):

    resp=fetch_get(False,art_json['url'],network_timeout,proxy)

    #print(resp)

    if resp is not None:

        soup=BeautifulSoup(resp,'html.parser')

        art_content=soup.find('div',itemprop=tag_id).find_all('p')

        content=map(lambda x:x.text,art_content)

        #print(list(content))

        new_content=''.join(list(content))

        art_json['content']=new_content

        art_json['inserttime']=time.strftime("%Y-%m-%d %X",time.localtime())

        print(art_json)

        time.sleep(random.randint(,))

if __name__=='__main__':

    site_name='indianexpress'

    max_main_interval,network_timeout,proxy=load_config(site_name)

    while True:

        get_list(load_urls('indianexpress'))

        print("{} all done ,sleep{} sec.".format(site_name,max_main_interval))

        time.sleep(max_main_interval)

        get_page()

pb_code.py

from configparser import ConfigParser

import json

import random

import requests

USER_AGENTS = [

    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",

    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",

    "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",

    "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",

    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",

    "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",

    "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",

    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",

    "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",

    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",

    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",

    "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",

    "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",

    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",

    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",

    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",

    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",

    "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",

    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",

    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",

    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",

    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",

    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",

    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",

    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",

    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",

    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"

]

def load_config(segment):

    '''从配置文件加载参数信息'''

    config=ConfigParser()

    config.read('config.ini','utf-8-sig')

    p1=int(config.get(segment,'max_main_interval'))

    p2=int(config.get(segment,'network_timeout'))

    p3=config.get(segment,'proxy')

    if p3=='':

        p3=None

    return p1,p2,p3

def load_urls(fname):

    '''加载采集url'''

    with open(fname+'.json',encoding='utf-8') as f:

        r =json.load(f)

        return r

def fetch_get(is_json,url,timeout,proxy):

    '''发送get请求并返回解析数据'''

    head={

        'User-Agent':random.choice(USER_AGENTS)

    }

    req=requests.get(url,headers=head,timeout=timeout,proxies={'http',proxy} if proxy else  None)

    if is_json:

        x=json.loads(req.text)

    else:

        x=req.text

    return x

def save_db(jdata):

    '''保存json到kafka:通过中转接口'''

    print("site_name:{} url{}".format(jdata['site_name'],jdata['url']))

    requests.post('',json=jdata,headers={"Content-Type": "application/json","keep_alive":'False'})

indianexpress.json

{

  "list_class": "articles",

  "page_content_id": "articleBody",

  "url": [

     "http://indianexpress.com/latest-news/"

  ]

}

栏目抓取网站日kafka的更多相关文章

抓取网站数据不再是难事了，Fizzler（So Easy）全能搞定
首先从标题说起,为啥说抓取网站数据不再难(其实抓取网站数据有一定难度),SO EASY!!!使用Fizzler全搞定,我相信大多数人或公司应该都有抓取别人网站数据的经历,比如说我们博客园每次发表完文章 ...
使用PHP抓取网站ico图标
网站许久没用更新,以后会经常更新,本次分享一个使用PHP抓取网站ico的程序,提供一个网站列表后对网站的ico进行下载抓取,具体代码如下: <?php /** * 更新热站ico * gao 2 ...
Python入门-编写抓取网站图片的爬虫-正则表达式
//生命太短我用Python! //Python真是让一直用c++的村里孩子长知识了! 这个仅仅是一个测试,成功抓取了某网站1000多张图片. 下一步要做一个大新闻大工程 #config = ut ...
【转】详解抓取网站，模拟登陆，抓取动态网页的原理和实现（Python，C#等）
转自:http://www.crifan.com/files/doc/docbook/web_scrape_emulate_login/release/html/web_scrape_emulate_ ...
利用wget 抓取网站网页包括css背景图片
利用wget 抓取网站网页包括css背景图片 wget是一款非常优秀的http/ftp下载工具,它功能强大,而且几乎所有的unix系统上都有.不过用它来dump比较现代的网站会有一个问题:不支持c ...
搜索会抓取网站域名的whoise信息吗
http://www.wocaoseo.com/thread-309-1-1.html 网站是否在信产部备案,这是不是会成为影响网站收录和排名的一个因素?百度是否会抓取域名注册人的相关whois信息吗 ...
C# 实现抓取网站页面内容
抓取新浪网的新闻栏目,如图所示: 使用谷歌浏览器的查看源代码: 通过分析得知,我们所要找的内容在以下两个标签之间: <!-- publish_helper name='要闻-新闻' p_id= ...
[Python爬虫] 之二十八：Selenium +phantomjs 利用 pyquery抓取网站排名信息
一.介绍本例子用Selenium +phantomjs爬取中文网站总排名(http://top.chinaz.com/all/index.html,http://top.chinaz.com/han ...
C# 抓取网站数据
项目主管说这是项目中的一个亮点(无语...), 类似于爬虫一类的东西,模拟登陆后台系统,获取需要的数据.然后就开始研究这个. 之前有一些数据抓取的经验,抓取流程无非:设置参数->服务端发送请求- ...

随机推荐

*Codeforces891E. Lust
$n \leq 5000$的数列,$k \leq 1e9$次操作,每次随机选一个数-1,然后把其他数的积加入答案.问最后答案期望,$mod \ \ 1e9+7$. 略微观察可以发现答案=初始数列的积- ...
Struts2牛逼的拦截器，卧槽这才是最牛的核心！
struts 拦截器一拦截器简介及简单的拦截器实例 Struts2拦截器是在访问某个Action或者Action的某个方法,在字段前或者之后实施拦截,并且Struts2拦截器是可以插拔的,拦截器是 ...
51NOD 1424 零树
Discription 有一棵以1为根的树,他有n个结点,用1到n编号.第i号点有一个值vi. 现在可以对树进行如下操作: 步骤1:在树中选一个连通块,这个连通块必须包含1这个结点. 步骤2:然后对这 ...
网络安全(超级详细)零基础带你一步一步走进缓冲区溢出漏洞和shellcode编写！
零基础带你走进缓冲区溢出,编写shellcode. 写在前面的话:本人是以一个零基础者角度来带着大家去理解缓冲区溢出漏洞,当然如果你是开发者更好. 注:如果有转载请注明出处!创作不易.谢谢合作. 0. ...
Raft算法详解
一致性算法Raft详解背景熟悉或了解分布性系统的开发者都知道一致性算法的重要性,Paxos一致性算法从90年提出到现在已经有二十几年了,而Paxos流程太过于繁杂实现起来也比较复杂,可能也是以为过 ...
win7配置java环境变量
http://jingyan.baidu.com/article/9f63fb91d87fb0c8400f0e93.html 安装JDK,从Oracel官方网站上下载,也可以通过搜索,进入链接.下载完 ...
Javascript：如何调用全局变量？
怎样使用全局变量呢? window.globalVariableName 参考: https://blog.csdn.net/zyz511919766/article/details/7276089
BUPT复试专题—统计时间间隔(2013计院)
题目描述给出两个时间(24小时制),求第一个时间至少要经过多久才能到达第二个时间.给出的时间一定满足的形式,其中x和y分别代表小时和分钟.0≤x<24,0≤y<60. 输入格式第一行为 ...
《C++ Primer Plus》学习笔记9
<C++ Primer Plus>学习笔记9 第15章友元.异常和其他 <<<<<<<<<<<<<<& ...
weexapp 开发流程（三）其他页面创建
1.首页 (1)轮播图步骤一:创建轮播图组件(Slider.vue) src / assets / components / Slider.vue  & ...

栏目抓取网站日kafka

栏目抓取网站日kafka的更多相关文章

随机推荐

热门专题