def main():
db = MongoDB()
while True:
def begin_callback():
log.info('\n********** proxies begin **********')
db.delete('proxies_urls')
def end_callback():
log.info('\n********** proxies end **********')
# 更新任务状态 done
# 导出数据
# export_data = ExportData(source_table = '', aim_table = '', key_map = '', unique_key = '')
# export_data.export_to_oracle()
# 配置spider
spider = Spider(tab_urls='proxies_urls',
tab_site='proxies_site_info',
tab_content='proxies_content_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params={},
content_unique_key='ip')
# 添加parser
spider.add_parser(gaoni_parser)
spider.start()
# time.sleep(60)
break
def main():
while True:
if task_status.is_doing: #done
log.debug('is doing sleep ...%ss' % SLEEP_TIME)
time.sleep(SLEEP_TIME)
continue
task_status.is_doing = True
keywords = Keywords().get_keywords()
def begin_callback():
log.info('\n********** spider_main begin **********')
def end_callback():
log.info('\n********** spider_main end **********')
task_status.is_doing = False
# 配置spider
spider = Spider(tab_list,
tab_unique_key_list,
tab_ensure_index_list,
parser_count=1,
site_parsers=parser_siteid_list,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=keywords)
# 添加parser
for parser in parser_list:
spider.add_parser(parser)
spider.start()
def main():
db = MongoDB()
def begin_callback():
log.info('\n********** wp begin **********')
db.delete('WP_urls', {})
def end_callback():
# 更新关键词状态 做完
log.info('\n********** wp end **********')
export_data.main()
# 配置spider
spider = Spider(tab_urls = 'WP_urls', tab_site = 'WP_site_info', tab_content = 'WP_content_info',
parser_count = 20, begin_callback = begin_callback, end_callback = end_callback,
content_unique_key = 'title')
# 添加parser
spider.add_parser(dongmanla_parser)
# spider.add_parser(zx_novel_parser)
# spider.add_parser(jisu_cartoon_parser)
# spider.add_parser(ximalaya_parser)
spider.start()
def main():
search_keyword1 = ['成龙']
search_keyword2 = []
search_keyword3 = []
def begin_callback():
log.info('\n********** VA begin **********')
def end_callback():
# 更新关键词状态 做完
log.info('\n********** VA end **********')
# 配置spider
spider = Spider(tab_urls='VA_urls',
tab_site='VA_site_info',
tab_content='VA_content_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
search_keyword1=search_keyword1,
search_keyword2=search_keyword2,
search_keyword3=search_keyword3)
# 添加parser
# spider.add_parser(baidu_parser)
# spider.add_parser(magnet_parser)
# spider.add_parser(netdisk_parser)
# spider.add_parser(weibo_parser)
# spider.add_parser(wechat_parser)
# spider.add_parser(soubaidupan_parser)
spider.add_parser(douban_parser)
spider.start()
def main():
db = MongoDB()
def begin_callback():
log.info('\n********** live_app begin **********')
db.delete('LiveApp_urls', {})
# db.update('LiveApp_anchor_info', {}, {"live_view" : 0})
# db.update('LiveApp_anchor_info', {}, {"watched_count" : 0})
def end_callback():
# 更新关键词状态 做完
log.info('\n********** live_app end **********')
# 配置spider
spider = Spider(tab_urls='LiveApp_urls',
tab_site='LiveApp_site_info',
tab_content='LiveApp_anchor_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
content_unique_key='name')
# 添加parser
spider.add_parser(inke_parser)
spider.add_parser(huajiao_parser)
spider.start()
def main():
db = OracleDB()
mongodb = MongoDB()
sql = 'select t.KEYWORD, t.monitor_type from TAB_MVMS_SEARCH_INFO t where sysdate >= t.monitor_start_time and sysdate <= t.monitor_end_time and search_type = 702'
result_list = db.find(sql, fetch_one=False)
if not result_list:
log.debug('无任务 结束')
return
parser_params = {'result_list': result_list}
# parser_params = []
# for i in result:
# parser_params.extend(str(i[0]).split(','))
def begin_callback():
log.info('\n********** WWA_weibo_user begin **********')
mongodb.delete('WWA_weibo_user_urls')
def end_callback():
# 导出数据
key_map = {
'id': 'int__id',
'name': 'str_name',
'sex': 'int_sex',
'summary': 'str_summary',
'fans_count': 'int_fans_count',
'blog_verified': 'str_blog_verified',
'is_verified': 'int_is_verified',
'account_url': 'str_url',
'follow_count': 'int_follow_count',
'image_url': 'str_image_url',
'monitor_status': 'vint_401',
'SEARCH_TYPE' : 'vint_702',
'region' : 'str_area'
}
export = ExportData('WWA_weibo_user_info', 'tab_mvms_weibo_info', key_map, 'account_url')
export.export_to_oracle()
log.info('\n********** WWA_weibo_user end **********')
# 配置spider
spider = Spider(tab_urls = 'WWA_weibo_user_urls', tab_site = 'WWA_site_info', tab_content = 'WWA_weibo_user_info',
parser_count = 1, begin_callback = begin_callback, end_callback = end_callback,
parser_params = parser_params)
# 添加parser
spider.add_parser(weibo_user_parser)
spider.start()
def main():
while True:
if task_status.is_doing:
log.debug('正在做 不取任务')
tools.delay_time(SEARCH_TASK_SLEEP_TIME)
continue
task_status.is_doing = True
# 查找任务
get_task_url = MASTER_ADDRESS + '/task/get_task'
print(get_task_url)
update_task_url = MASTER_ADDRESS + '/task/update_task'
data = tools.get_json_by_requests(get_task_url)
# tasks = [[209690, '百度新闻', 11, 'http://news.baidu.com/?tn=news', 3]]
print(data)
tasks = data.get('tasks', [])
parser_count = data.get('thread_count')
def begin_callback():
log.info('\n********** news begin **********')
# 更新任务状态 doing
data = {'tasks': str(tasks), 'status': 602}
if tools.get_json_by_requests(update_task_url, data=data):
log.debug('更新任务状态 正在做...')
def end_callback():
log.info('\n********** news end **********')
task_status.is_doing = False
data = {'tasks': str(tasks), 'status': 603}
if tools.get_json_by_requests(update_task_url, data=data):
log.debug('更新任务状态 已做完！')
# 配置spider
spider = Spider(tab_urls='news:news_urls',
parser_count=parser_count,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=tasks,
delete_tab_urls=False)
# 添加parser
spider.add_parser(news_parser)
spider.start()
def main():
search_task_sleep_time = int(
tools.get_conf_value('config.conf', 'task', 'search_task_sleep_time'))
# 更新任务状态 正在做的更新为等待
while True:
# 查询任务状态 有正在做的 sleep contine
# TODO
search_keyword1 = ['hi']
search_keyword2 = ['hello']
search_keyword3 = ['hello, hi']
task_id = 1
# 任务为空 sleep continue
# TODO
def begin_callback():
log.info('\n********** template begin **********')
# 更新任务状态 doing
def end_callback():
log.info('\n********** template end **********')
# 更新任务状态 done
# 导出数据
# export_data = ExportData(source_table = '', aim_table = '', key_map = '', unique_key = '')
# export_data.export_to_oracle()
# 配置spider
# spider = Spider(tab_urls = 'template_urls', tab_site = 'template_site_info', tab_content = '', parser_count = 1, begin_callback = begin_callback, end_callback = end_callback)
spider = Spider(tab_urls='template_urls',
tab_site='template_site_info',
tab_content='template_content_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
search_keyword1=search_keyword1,
search_keyword2=search_keyword2,
search_keyword3=search_keyword3)
# 添加parser
spider.add_parser(xxx_parser)
spider.add_parser(yyy_parser)
spider.start()
# time.sleep(search_task_sleep_time)
break
def main():
db = MongoDB()
db.set_unique_key('WWA_app_vioation_content_info', 'url')
db.set_ensure_index('WWA_app_vioation_content_info', 'read_status')
def begin_callback():
log.info('\n********** WWA_APP begin **********')
db.delete('WWA_app_urls', {})
def end_callback():
export_data.main()
log.info('\n********** WWA_APP end **********')
# 配置spider
spider = Spider(tab_urls = 'WWA_app_urls', tab_site = 'WWA_app_site_info', tab_content = 'WWA_app_content_info', parser_count = 1, begin_callback = begin_callback, end_callback = end_callback, parser_params = {})
# 添加parser
spider.add_parser(headline_parser)
spider.add_parser(kuaibao_parser)
spider.start()
def main():
oracledb = OracleDB()
sql = 'select t.KEYWORD, t.monitor_type from TAB_MVMS_SEARCH_INFO t where sysdate >= t.monitor_start_time and sysdate <= t.monitor_end_time and search_type = 701'
result_list = oracledb.find(sql) #[(keys, monitor_type),()]
if not result_list:
log.debug('无任务 结束')
return
# print(result_list)
# keywords = []
# for result in result_list:
# keywords.extend(result[0].split(','))
def begin_callback():
log.info('\n********** WWA_wechat_account begin **********')
db = MongoDB()
db.delete('WWA_wechat_account_url', {})
def end_callback():
log.info('\n********** WWA_wechat_account end **********')
export_data.account_main()
parser_params = {'result_list': result_list}
# 配置spider
spider = Spider(tab_urls='WWA_wechat_account_url',
tab_site='WWA_wechat_site_info',
tab_content='WWA_wechat_official_accounts',
content_unique_key='account_id',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=parser_params)
# 添加parser
spider.add_parser(wechat_account_parser)
spider.start()
def main():
oracledb = OracleDB()
sql = 'select t.account_id, t.monitor_type from TAB_MVMS_WECHAT_INFO t where monitor_status = 402'
result_list = oracledb.find(sql)
if not result_list:
log.debug('无任务 结束')
return
# keywords = []
# for result in result_list:
# keywords.append(result[0])
def begin_callback():
log.info('\n********** WWA_wechat_article begin **********')
db = MongoDB()
db.delete('WWA_wechat_article_url', {})
def end_callback():
log.info('\n********** WWA_wechat_article end **********')
export_data.article_main()
parser_params = result_list
# 配置spider
spider = Spider(tab_urls='WWA_wechat_article_url',
tab_site='WWA_wechat_site_info',
tab_content='WWA_wechat_article',
content_unique_key='title',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=parser_params)
# 添加parser
spider.add_parser(wechat_article_parser)
spider.start()
def main():
db = OracleDB()
sql = '''
select t.program_id, c.chan_name, program_name, d.name, t.image_url, t.official_blog
from TAB_MMS_PROGRAM t
left join tab_mam_chan c
on c.chan_id = t.chan_id
left join tab_mms_dictionary d
on t.type = d.id
and d.type = 2
'''
# where t.program_id = 226
program_info = db.find(sql)
def begin_callback():
log.info('\n********** news begin **********')
# 更新任务状态 doing
def end_callback():
log.info('\n********** news end **********')
# 配置spider
spider = Spider(tab_urls='mms_urls',
begin_callback=begin_callback,
end_callback=end_callback,
delete_tab_urls=True,
parser_params=program_info)
# 添加parser
# spider.add_parser(iqiyi_hot_parser)
spider.add_parser(iqiyi_search_parser)
# spider.add_parser(weibo_user_parser)
# spider.add_parser(weibo_article_parser)
spider.start()
def main():
def begin_callback():
log.info('\n********** VA_APP begin **********')
db = MongoDB()
db.delete('VAApp_urls', {})
def end_callback():
export_data.main()
log.info('\n********** VA_APP end **********')
# 配置spider
spider = Spider(tab_urls='VAApp_urls',
tab_site='VAApp_site_info',
tab_content='VAApp_content_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params={})
# 添加parser
spider.add_parser(headline_parser)
spider.add_parser(kuaibao_parser)
spider.start()
def main():
def begin_callback():
# mongo_db = MongoDB()
# mongo_db.update('ZHEJIANG_APP_urls', {'depth': 0}, {'status': 0})
log.info('\n********** spider_main begin **********')
def end_callback():
log.info('\n********** spider_main end **********')
# 配置spider
spider = Spider(tab_list,
tab_unique_key_list,
tab_ensure_index_list,
parser_count=1,
site_parsers=parser_siteid_list,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params={})
# 添加parser
for parser in parser_list:
spider.add_parser(parser)
spider.start()
def main():
db = MongoDB()
oracle = OracleDB()
def begin_callback():
#db.update('WWA_app_urls',{'depth':0}, {'status':0})
db.delete('WWA_search_app_urls')
log.info('\n********** wwa begin **********')
def end_callback():
log.info('\n********** wwa end **********')
export_data.main()
keywords = []
result_list = oracle.find(
'select keyword from TAB_MVMS_SEARCH_INFO where MONITOR_START_TIME <= sysdate AND MONITOR_END_TIME >= sysdate and search_type=703'
)
if not result_list:
log.debug('无任务 结束')
return
keywords = []
for result in result_list:
keywords.extend(result[0].split(','))
parser_params = {'keywords': keywords}
# 配置spider
spider = Spider(tab_urls='WWA_search_app_urls',
tab_site='WWA_search_app_site_info',
tab_content='WWA_search_app_content_info',
content_unique_key='title',
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=parser_params)
# 添加parser
spider.add_parser(yingyongbao_parser)
spider.add_parser(android_market_parser)
spider.add_parser(baidu_mobile_assistant_parser)
spider.add_parser(mobile360_assistant_parser)
spider.start()
def main():
def begin_callback():
db.update('GameApp_urls', {'depth': 0}, {'status': 0})
log.info('\n********** game_app begin **********')
def end_callback():
log.info('\n********** game_app end **********')
# 配置spider
spider = Spider(tab_urls='GameApp_urls',
tab_site='GameApp_site_info',
tab_content='GameApp_content_info',
begin_callback=begin_callback,
end_callback=end_callback)
# 添加parser
spider.add_parser(yingyongbao_parser)
spider.add_parser(android_market_parser)
spider.add_parser(baidu_mobile_assistant_parser)
spider.add_parser(mobile360_assistant_parser)
spider.start()
def main():
search_task_sleep_time = int(
tools.get_conf_value('config.conf', 'task', 'search_task_sleep_time'))
db = OracleDB()
# 更新符合日期条件的任务状态 未做
sql = 'update tab_ivms_task_info t set t.task_status = 501 where sysdate >= t.monitor_start_time and sysdate <= t.monitor_end_time'
db.update(sql)
# 更新关键词状态 未做
sql = 'update tab_ivms_task_keyword k set k.finish_status = 601 where k.task_id in (select t.task_id from tab_ivms_task_info t where sysdate >= t.monitor_start_time and sysdate <= t.monitor_end_time)'
db.update(sql)
while True:
# 查任务
log.debug('查询任务...')
sql = 'select t.task_id from TAB_IVMS_TASK_INFO t where sysdate >= t.monitor_start_time and sysdate <= t.monitor_end_time and t.task_status = 501'
result = db.find(sql, fetch_one=True)
if not result:
break
task_id = result[0]
while True:
# 查看是否有正在执行的任务
sql = 'select t.* from TAB_IVMS_TASK_KEYWORD t where t.task_id = %d and finish_status = 602' % task_id
do_task = db.find(sql, fetch_one=True)
if do_task:
time.sleep(search_task_sleep_time)
continue
sql = 'select t.* from TAB_IVMS_TASK_KEYWORD t where t.task_id = %d and finish_status = 601' % task_id
result = db.find(sql, fetch_one=True)
if not result:
break
keyword_id = result[0]
task_id = result[1]
search_keyword1 = []
search_keyword2 = result[2].split(',') if result[2] else []
search_keyword3 = result[3].split(',') if result[3] else []
def begin_callback():
log.info('\n********** VA begin **********')
# 更新任务状态 正在做
sql = 'update TAB_IVMS_TASK_INFO set task_status = 502 where task_id = %d' % task_id
db.update(sql)
# 更新关键词状态 正在做
sql = 'update tab_ivms_task_keyword set finish_status = 602 where id = %d' % keyword_id
db.update(sql)
def end_callback():
# 更新关键词状态 做完
sql = 'update tab_ivms_task_keyword set finish_status = 603 where id = %d' % keyword_id
db.update(sql)
# 如果该任务的所有关键词都做完 则更新任务状态为做完
sql = 'select t.* from tab_ivms_task_keyword t where task_id = %d and finish_status = 601' % task_id
results = db.find(sql)
if not results:
# 导出数据
key_map = {
'program_id': 'vint_sequence.nextval',
'search_type': 'int_search_type',
'program_name': 'str_title',
'program_url': 'str_url',
'release_date': 'date_release_time',
'image_url': 'str_image_url',
'program_content': 'str_content',
'task_id': 'vint_%d' % task_id,
'keyword': 'str_keyword',
'keyword_count': 'int_keyword_count',
'check_status': 'vint_202'
}
export = ExportData('VA_content_info',
'tab_ivms_program_info', key_map,
'program_url')
export.export_to_oracle()
# 更新任务状态 做完
sql = 'update TAB_IVMS_TASK_INFO set task_status = 503 where task_id = %d' % task_id
db.update(sql)
log.info('\n********** VA end **********')
# 配置spider
spider = Spider(tab_urls='VA_urls',
tab_site='VA_site_info',
tab_content='VA_content_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
search_keyword1=search_keyword1,
search_keyword2=search_keyword2,
search_keyword3=search_keyword3)
# 添加parser
spider.add_parser(baidu_parser)
spider.add_parser(magnet_parser)
spider.add_parser(netdisk_parser)
spider.add_parser(weibo_parser)
spider.add_parser(wechat_parser)
spider.add_parser(soubaidupan_parser)
spider.add_parser(douban_parser)
spider.start()
time.sleep(search_task_sleep_time)
def main():
def begin_callback():
log.info('\n********** spider_article begin **********')
def end_callback():
log.info('\n********** spider_article end **********')
# 配置spider
spider = Spider(tab_urls='article_urls',
tab_site='article_site_info',
tab_content='article_text_info',
parser_count=40,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params={})
# 添加parser
spider.add_parser(cctv_parser)
spider.add_parser(ifeng_parser)
spider.add_parser(xinhua_parser)
spider.add_parser(tencent_parser)
spider.add_parser(sohu_parser)
spider.add_parser(wangyi_parser)
spider.add_parser(people_parser)
spider.add_parser(sina_parser)
spider.start()
def main():
db = MongoDB()
def begin_callback():
log.info('\n********** template begin **********')
db.delete('op_urls', {})
db.delete('op_content_info', {})
def end_callback():
log.info('\n********** template end **********')
# 更新任务状态 done
# 导出数据
# export_data = ExportData(source_table = '', aim_table = '', key_map = '', unique_key = '')
# export_data.export_to_oracle()
# 配置spider
spider = Spider(tab_urls='op_urls',
tab_site='op_site_info',
tab_content='op_content_info',
parser_count=20,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params={})
#添加parser
spider.add_parser(luzhou_parser)
spider.add_parser(longmatan_parser)
spider.add_parser(naxi_parser)
spider.add_parser(luxian_parser)
spider.add_parser(hejiang_parser)
spider.add_parser(gulin_parser)
spider.add_parser(luzhouzhiye_parser)
spider.add_parser(sichuanhuagong_parser)
spider.add_parser(luzhougaozhong_parser)
spider.add_parser(xuyong_parser)
spider.add_parser(jiangyang_parser)
spider.add_parser(luzhoutianli_parser)
spider.add_parser(sichuanluxian_parser)
spider.add_parser(sichuan_police_parser)
spider.add_parser(sichuanyikeda_parser)
spider.add_parser(luzhoubaidu_parser)
spider.start()
def main():
db = OracleDB()
mongodb = MongoDB()
sql = 'select t.ID, t.monitor_type from TAB_MVMS_WEIBO_INFO t where monitor_status = 402'
result_list = db.find(sql, fetch_one=False)
if not result_list:
log.debug('无任务 结束')
return
parser_params = result_list
# for i in result:
# parser_params.extend(str(i[0]).split(','))
def begin_callback():
log.info('\n********** WWA_weibo_info begin **********')
mongodb.delete('WWA_weibo_info_urls')
def end_callback():
# 导出数据
key_map = {
'id': 'int__id',
'release_time': 'date_release_time',
'come_from': 'str_come_from',
'content': 'clob_content',
'image_url': 'str_image_url',
'video_url': 'str_video_url',
'transpond_count': 'int_transpond_count',
'praise_count': 'int_praise_count',
'check_status': 'vint_301',
'weibo_id': 'int_weibo_id',
'article_url': 'str_url',
'violate_status': 'int_violate_id',
'sensitive_id': 'int_sensitive_id',
'record_time': 'date_record_time',
'SEXY_IMAGE_STATUS': 'str_sexy_image_status'
}
export = ExportData('WWA_weibo_info_info',
'tab_mvms_weibo_article_info',
key_map,
unique_key='ARTICLE_url',
condition={
'read_status': 0,
"image_pron_status": 2
})
export.export_to_oracle()
log.info('\n********** WWA_weibo_info end **********')
# 配置spider
spider = Spider(tab_urls='WWA_weibo_info_urls',
tab_site='WWA_site_info',
tab_content='WWA_weibo_info_info',
parser_count=1,
begin_callback=begin_callback,
end_callback=end_callback,
parser_params=parser_params)
# 添加parser
spider.add_parser(weibo_info_parser)
spider.start()