栏目抓取网站日kafka

[indianexpress]max_main_interval=1800network_timeout=15proxy=

#!/usr/bin/python3#-*- coding:utf-8 -*-"""create 2018-02-27author zldesc: ???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,bs4usage: ???skip"""from pb_code import *from bs4 import BeautifulSoupimport reimport timedef 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[0],"%B %d, %Y %H:%M")))+3600*2.5 ???????????????????if ‘pm‘ in timedate: ???????????????????????timestamp=timestamp+3600*12 ???????????????????if int(time.time())-timestamp<3600: ???????????????????????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":"7", ???????????????????????????"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(3,10))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(3,10))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()

from configparser import ConfigParserimport jsonimport randomimport requestsUSER_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,p3def load_urls(fname): ???‘‘‘加载采集url‘‘‘ ???with open(fname+‘.json‘,encoding=‘utf-8‘) as f: ???????r =json.load(f) ???????return rdef 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 xdef 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‘})

{ ?"list_class": "articles", ?"page_content_id": "articleBody", ?"url": [ ????"http://indianexpress.com/latest-news/" ?]}