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

UVa1363 Joseph's Problem
把整个序列进行拆分成[k,k/2),[k/2, k/3), [k/3,k/4)...k[k/a, k/b)的形式,对于k/i(整除)相同的项,k%i成等差数列. /*by SilverN*/ #inc ...
扰动法--*BZOJ3157: 国王奇遇记
求$\sum_{i=1}^ni^mm^i$.$n \leq 1e9,m \leq 200$. 其实我也不知道这东西为啥叫“扰动法”,大概是在黑暗的边缘试探?就是那种,人家再多一点就被您看破了,然后您就 ...
计算机windows7连接打印机
计算机连接打印机 (1)查看打印机的名字. 示例,打印机名为 HP LaserJet M1522 .... (2)打开windows开始菜单,点击[设备和打印机],然后查看打印机和传真那个区域是否有打 ...
不拖控件的asp.net编程方法——第1回
以前写的asp.net程序基本上都用了webfrom的控件编写的,当然有个好处就是易入门.快速效率高,但感觉自己这了几个小系统,还是没学到什么东西,感觉心里没底,因为都是封装好的东西,拿来就用的,功能 ...
LL(1)语法分析器 //c++实现
#include<iostream> #include<string> #include<map> #include<vector> #include& ...
luogu P3865 【模板】ST表
题目背景这是一道ST表经典题——静态区间最大值请注意最大数据时限只有0.8s,数据强度不低,请务必保证你的每次查询复杂度为 O(1)O(1) 题目描述给定一个长度为 NN 的数列,和 MM 次询 ...
转：c++ 11 新特性
声明:本文源自 Danny Kalev 在 2011 年 6 月 21 日发表的<The Biggest Changes in C++11(and Why You Should Care)&g ...
解决Linux系统没有/etc/sysconfig/iptables文件
Linux系统中,防火墙默认是不开启的,一般也没有配置过任何防火墙的策略,所以不存在/etc/sysconfig/iptables文件. 一.常规解决方法: 1.在控制台使用iptables命令随便写 ...
【Java编程】建立一个简单的JDBC连接-Drivers, Connection, Statement and PreparedStatement
本blog提供了一个简单的通过JDBC驱动建立JDBC连接例程.并分别通过Statement和PreparedStatement实现对数据库的查询. 在下一篇blog中将重点比較Statement与P ...
Linux C++的多线程编程（转）
1. 引言线程(thread)技术早在60年代就被提出,但真正应用多线程到操作系统中去,是在80年代中期,solaris是这方面的佼佼者.传统的Unix也支持线程的概念,但是在一个进程(proces ...

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