RT
代碼如下:
from pyspider.libs.base_handler import *
from pyspider.libs.utils import md5string
import logging
fhandler = logging.FileHandler('/tmp/aaaa')
class Handler(BaseHandler):
retry_delay = {
0: 1,
1: 1*5,
2: 2*5,
3: 3*5,
4: 4*5,
5: 5*5,
6: 1*30,
7: 1*40,
8: 1*60,
9: 2*60,
10: 2*60,
'': 3*60
}
crawl_config = {
'force_update': True,
'retries': 99,
'auto_recrawl': False,
'proxy': "xxxxxxxxxxxxxxxxxxx",
'itag': 'v0007',
'headers': {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,zh-TW;q=0.7',
'Cache-Control': 'max-age=0',
'User-Agent':'ozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
}
}
def __init__(self):
self.kw = '春裝2018春款'
self.base_url = 'https://pub.alimama.com/promo/search/index.htm?q=%s&toPage=%s&perPageSize=50'
self.page_num = 1
self.total_num = 1
logger.addHandler(fhandler)
def get_taskid(self, task):
"""md5string(task['url']+json.dumps(task['fetch'].get('data', '')))"""
return super(Handler, self).get_taskid(task)
def on_message(self, project, msg):
pass
def on_result(self, result):
# pyspider result_worker --result-cls "myresult.MyResultWorker"
logger.info('on_resultttttttttttt')
super(Handler, self).on_result(result)
def on_finished(self, response, task):
logger.info('on_finishedddddddddd')
pass
@every(minutes=5)
def on_start(self):
while self.page_num <= self.total_num:
url = self.base_url%(self.kw, self.page_num)
self.crawl(url, fetch_type='js', callback=self.index_page)
self.page_num += 1
@config(age=3 * 60)
def index_page(self, response):
scode = 404
for each in response.doc('div.block-search-box').items():
scode = 200
save = {}
save['title'] = each('a.color-m').text()
self.crawl(each('a.color-m').attr.href.replace('http://','https://'), connect_timeout=50, fetch_type='js', callback=self.detail_page, save=save)
# 標記為失敗準備重試
if scode != 200:
response.status_code = scode
response.raise_for_status()
@config(priority=0, age=3 * 60)
def detail_page(self, response):
#response.content = response.content.decode('gbk', 'ignore').encode('gbk')
save = response.save
#logger.info(response.doc('.tb-rmb-num').text())
return {
"url": response.url,
"title": save['title']
}
[I 180317 18:50:00 scheduler:965] select z_taobao_a:_on_cronjob data:,_on_cronjob
[I 180317 18:50:56 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:51:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:52:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:53:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:54:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:55:00 scheduler:965] select z_taobao_a:_on_cronjob data:,_on_cronjob
[I 180317 18:55:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:56:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:57:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:58:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 18:59:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:00:00 scheduler:965] select z_taobao_a:_on_cronjob data:,_on_cronjob
[I 180317 19:00:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:01:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:02:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:03:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:04:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
[I 180317 19:05:00 scheduler:965] select z_taobao_a:_on_cronjob data:,_on_cronjob
[I 180317 19:05:57 scheduler:586] in 5m: new:0,success:0,retry:0,failed:0
是我那里的配置問題嗎?
北大青鳥APTECH成立于1999年。依托北京大學優(yōu)質(zhì)雄厚的教育資源和背景,秉承“教育改變生活”的發(fā)展理念,致力于培養(yǎng)中國IT技能型緊缺人才,是大數(shù)據(jù)專業(yè)的國家
北大青鳥中博軟件學院創(chuàng)立于2003年,作為華東區(qū)著名互聯(lián)網(wǎng)學院和江蘇省首批服務外包人才培訓基地,中博成功培育了近30000名軟件工程師走向高薪崗位,合作企業(yè)超4
中公教育集團創(chuàng)建于1999年,經(jīng)過二十年潛心發(fā)展,已由一家北大畢業(yè)生自主創(chuàng)業(yè)的信息技術與教育服務機構(gòu),發(fā)展為教育服務業(yè)的綜合性企業(yè)集團,成為集合面授教學培訓、網(wǎng)
達內(nèi)教育集團成立于2002年,是一家由留學海歸創(chuàng)辦的高端職業(yè)教育培訓機構(gòu),是中國一站式人才培養(yǎng)平臺、一站式人才輸送平臺。2014年4月3日在美國成功上市,融資1
曾工作于聯(lián)想擔任系統(tǒng)開發(fā)工程師,曾在博彥科技股份有限公司擔任項目經(jīng)理從事移動互聯(lián)網(wǎng)管理及研發(fā)工作,曾創(chuàng)辦藍懿科技有限責任公司從事總經(jīng)理職務負責iOS教學及管理工作。
浪潮集團項目經(jīng)理。精通Java與.NET 技術, 熟練的跨平臺面向?qū)ο箝_發(fā)經(jīng)驗,技術功底深厚。 授課風格 授課風格清新自然、條理清晰、主次分明、重點難點突出、引人入勝。
精通HTML5和CSS3;Javascript及主流js庫,具有快速界面開發(fā)的能力,對瀏覽器兼容性、前端性能優(yōu)化等有深入理解。精通網(wǎng)頁制作和網(wǎng)頁游戲開發(fā)。
具有10 年的Java 企業(yè)應用開發(fā)經(jīng)驗。曾經(jīng)歷任德國Software AG 技術顧問,美國Dachieve 系統(tǒng)架構(gòu)師,美國AngelEngineers Inc. 系統(tǒng)架構(gòu)師。