def crawl(self):
cid = self.key
channel = CHANNELS[int(cid)]
page = 1
pagesize = 30
while 1:
try:
data = api_shows(cid, page, pagesize)
if data is not None:
page += 1
else:
return
except:
self.logger.warning(get_exception_info())
continue
if not data.get('results'):
break
for item in data['results']:
try:
show_id = item['tid']
reset = (item['completed'] == 0)
data = {
'channel': channel,
'image': item.get('show_vthumburl_hd') if item.get('show_vthumburl_hd') else item.get('show_thumburl_hd'),
'image2': item.get('show_thumburl_hd')
}
Scheduler.schedule(
AlbumCrawler.type, key=show_id, data=data, reset=reset)
except:
self.logger.warning(get_exception_info())
def crawl(self):
cid = self.key
page = 1
pagesize = 30
while True:
list_data = api_list(cid, page, pagesize)
# 数据不为空，取出数据，page+=1
if list_data.get('results'):
for item in list_data.get('results'):
# m = re.match("^\d+$", item['tid'])
# if m:
source_id = item['tid']
reset = int(item['completed']) == 0
Scheduler.schedule(
type=AlbumCrawler.type,
key=str(source_id),
reset=reset
)
page += 1
# 数据为空跳出循环
if not list_data.get('results'):
if page > 100:
return
else:
page += 1
def crawl(self):
cid = self.key
page = 1
pagesize = 30
while True:
list_data = api_list(cid, page, pagesize)
# 数据不为空，取出数据，page+=1
if list_data.get('results'):
for item in list_data.get('results'):
# m = re.match("^\d+$", item['tid'])
# if m:
source_id = item['tid']
reset = int(item['completed']) == 0
Scheduler.schedule(type=AlbumCrawler.type,
key=str(source_id),
reset=reset)
page += 1
# 数据为空跳出循环
if not list_data.get('results'):
if page > 100:
return
else:
page += 1
def crawler_job(request):
if request.method == "GET":
url = request.GET.get('url', None)
raw_job = Scheduler.get_job_from_url(url)
job = {}
if raw_job:
job = {
'type': raw_job['type'],
'key': raw_job['key'],
'priority': raw_job['priority'],
'interval': raw_job['interval'],
'lastrun': raw_job['lastrun'],
'status': raw_job['status'],
'to_album_id': raw_job['data'].get('to_album_id'),
}
return job
else:
url = request.GET.get('url', None)
interval = request.GET.get('interval', 3600)
channel = request.GET.get('channel', None)
image = request.GET.get('image', None)
data = {
'channel':channel,
'image': image,
}
success = Scheduler.schedule_url(url, data=data, interval=int(interval), reset=True)
return {'status': int(success)}
def crawl(self):
cid = self.key
channel = self.data.get("channel_name")
itemid = 0
date = 0
areaid = 0
sort = 2 # 1:最新 2:最热
start = 0
num = 30
while True:
list_data = api_list(cid, itemid, date, areaid, sort, start, num,
pcode, version)
list_data = list_data.get("body")
if list_data.get("data"):
for item in list_data['data']:
source_id = item.get("id")
image = item.get("icon")
reset = int(item['isend']) == 0
Scheduler.schedule(type=AlbumCrawler.type,
key=source_id,
data={
"channel": channel,
"image": image
},
reset=reset)
start += 1
if not list_data.get("data"):
return
def crawl(self):
cid = self.key
channel = self.data.get("channel_name")
itemid = 0
date = 0
areaid = 0
sort = 2 # 1:最新 2:最热
start = 0
num = 30
while True:
list_data = api_list(
cid, itemid, date, areaid, sort, start, num, pcode, version)
list_data = list_data.get("body")
if list_data.get("data"):
for item in list_data['data']:
source_id = item.get("id")
image = item.get("icon")
reset = int(item['isend']) == 0
Scheduler.schedule(
type=AlbumCrawler.type,
key=source_id,
data={
"channel": channel,
"image": image
},
reset=reset
)
start += 1
if not list_data.get("data"):
return
def init(conf=None):
if not conf:
conf = {}
for cid in CHANNELS.keys():
Scheduler.schedule(CategoryCrawler.type,
key=str(cid),
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600))
def crawl(self):
min_time = self.data.get('updated',
datetime.min) if self.data else datetime.min
max_time = None
time = None
page = 1
while True:
url = "http://www.265zy.com/list/?0-%s.html" % page
hxs = load_html(url)
for s in hxs.select("//body/.//tr[@class='row']"):
try:
href = s.select("td[1]/a/@href").extract()[0]
source_id = re.findall("(\d+)\.html", href)[0]
title = clean_title(
s.select("td[1]/.//text()").extract()[0])
region = s.select("td[2]/.//text()").extract()[0].replace(
u"地区", u"")
category = s.select("td[3]/.//text()").extract()[0]
time = s.select("td[4]/.//text()").extract()[0]
time = datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
except:
continue
if not max_time:
max_time = time
if time < min_time:
break
data = {
"title": title,
"time": time,
'category': category,
'region': region,
}
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get(
"time", datetime.min) if lastdata else datetime.min
Scheduler.schedule(type=AlbumCrawler.type,
key=source_id,
data=data,
reset=data['time'] > lasttime)
if time and time < min_time:
break
text = hxs.select("//div[@class='pages']/span/text()").extract()[0]
page_count = int(re.findall(u"\d+/(\d+)页", text)[0])
if page >= 5:
break
page += 1
if max_time:
if not self.data:
self.data = {}
self.data['updated'] = max_time
def init(conf=None):
if not conf:
conf = {}
for catecode in CHANNELS.keys():
Scheduler.schedule(CategoryCrawler.type,
key=str(catecode),
data={"catecode": catecode},
priority=conf.get('priority', Priority.Normal),
interval=conf.get('interval', 3600))
def init(conf=None):
if not conf:
conf = {}
for channel in CHANNELS.iterkeys():
Scheduler.schedule(HistoryCrawler.type,
key=channel,
data={"year": 1900},
priority=conf.get('priority', Priority.Normal),
interval=conf.get('interval', 86400))
def init(conf=None):
if not conf:
conf = {}
for id in _CHANNEL_DCT.iterkeys():
Scheduler.schedule(CategoryCrawler.type,
key=str(id),
data={"cid": id},
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600))
def init(conf=None):
if not conf:
conf = {}
Scheduler.schedule(
ListCrawler.type, #爬虫类型
key="", #该类型只有一个实例,key设""
priority=conf.get('priority', Priority.High), #优先级为高
data={'updated': datetime.min}, #附加数据为上次爬取到的最新视频的更新时间
interval=conf.get('interval', 3600) #循环抓取间隔为1小时
)
def init(conf = None):
if not conf:
conf = {}
Scheduler.schedule(
ListCrawler.type, #爬虫类型
key = "", #该类型只有一个实例,key设""
priority = conf.get('priority', Priority.High), #优先级为高
data = {'updated' : datetime.min}, #附加数据为上次爬取到的最新视频的更新时间
interval = conf.get('interval', 3600) #循环抓取间隔为1小时
)
def init(conf=None):
if not conf:
conf = {}
for id, channel in CHANNELS.iteritems():
data = {"channel": channel}
Scheduler.schedule(ListCrawler.type,
key=id,
data=data,
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600))
def init(conf = None):
if not conf:
conf = {}
Scheduler.schedule(
ListCrawler.type, #鐖櫕绫诲瀷
key = "", #璇ョ被鍨嬪彧鏈変竴涓疄渚�,key璁�""
priority = conf.get('priority', Priority.High), #浼樺厛绾т负楂�
data = {'updated' : datetime.min}, #闄勫姞鏁版嵁涓轰笂娆＄埇鍙栧埌鐨勬渶鏂拌棰戠殑鏇存柊鏃堕棿
interval = conf.get('interval', 3600) #寰幆鎶撳彇闂撮殧涓�忔椂
)
def init(conf=None):
if not conf:
conf = {}
for key, data in CHANNELS.iteritems():
Scheduler.schedule(
ListCrawler.type,
key=key,
data=data,
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600)
)
def crawl(self):
min_time = self.data.get('updated', datetime.min) if self.data else datetime.min
max_time = None
time = None
page = 1
while True:
url = "http://zyqvod.com/?page=%s" % page
hxs = load_html(url)
for s in hxs.select("//table[@id='listTable']/tbody/tr"):
try:
source_id = re.findall("id=(\d+)", s.select("td[1]/a/@href").extract()[0])[0]
title = clean_title(s.select("td[1]/.//text()").extract()[0])
category = s.select("td[2]/.//text()").extract()[0]
region = s.select("td[3]/.//text()").extract()[0]
completed = s.select("td[4]/.//text()").extract()[0] == u"完结"
time = s.select("td[5]/.//text()").extract()[0]
time = datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
except:
continue
if not max_time:
max_time = time
if time < min_time:
break
data = {
"title" : title,
"time" : time,
'category' : category,
'region' : region,
'completed' : completed,
}
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get("time", datetime.min) if lastdata else datetime.min
Scheduler.schedule(type = AlbumCrawler.type, key = source_id, data = data, reset = data['time'] > lasttime)
if time and time < min_time:
break
text = hxs.select("//div[@class='page_num']/text()").extract()[0]
page_count = int(re.findall(u"\d+/(\d+)页", text)[0])
if page >= page_count:
break
page += 1
if max_time:
if not self.data:
self.data = {}
self.data['updated'] = max_time
def init(conf=None):
if not conf:
conf = {}
data = api_channel(pcode, version)
for channel in data['body']['channel']:
cid = channel.get("cid")
channel_name = channel.get("name")
crawl_data = {
"channel_id": cid,
"channel_name": channel_name,
}
Scheduler.schedule(ListCrawler.type, key=cid, data=crawl_data, priority=conf.get(
'priority', Priority.High), interval=conf.get('interval', 3600))
def crawl(self):
min_time = self.data.get('updated', datetime.min) if self.data else datetime.min
max_time = None
time = None
page = 1
while True:
url = "http://www.265zy.com/list/?0-%s.html" % page
hxs = load_html(url)
for s in hxs.select("//body/.//tr[@class='row']"):
try:
href = s.select("td[1]/a/@href").extract()[0]
source_id = re.findall("(\d+)\.html", href)[0]
title = clean_title(s.select("td[1]/.//text()").extract()[0])
region = s.select("td[2]/.//text()").extract()[0].replace(u"地区", u"")
category = s.select("td[3]/.//text()").extract()[0]
time = s.select("td[4]/.//text()").extract()[0]
time = datetime.strptime(time, "%Y-%m-%d %H:%M:%S")
except:
continue
if not max_time:
max_time = time
if time < min_time:
break
data = {
"title" : title,
"time" : time,
'category' : category,
'region' : region,
}
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get("time", datetime.min) if lastdata else datetime.min
Scheduler.schedule(type = AlbumCrawler.type, key = source_id, data = data, reset = data['time'] > lasttime)
if time and time < min_time:
break
text = hxs.select("//div[@class='pages']/span/text()").extract()[0]
page_count = int(re.findall(u"\d+/(\d+)页", text)[0])
if page >= 5:
break
page += 1
if max_time:
if not self.data:
self.data = {}
self.data['updated'] = max_time
def crawl(self):
type = 3
channel_id = self.key
channel = self.data['channel']
start = 0
num = 16
params = {
"order": "times",
"time": "today"
}
while 1:
list_data = api_list(type, channel_id, start, num, params)
if start == list_data['num']:
return
for item in list_data['data']:
if channel in LONG_VIDEO_CHANNELS.values():
source_id = item['mid']
tags = []
time = item['public_time']
time = datetime.strptime(time, "%Y%m%d")
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get(
"time", datetime.min) if lastdata else datetime.min
reset = time > lasttime
else:
source_id = item['flvid']
tags = item.get("tags").split(",")
time = datetime.utcnow()
reset = False
data = {
"url": item.get("web_url"),
"title": item.get("title"),
"image": item.get("bpic"),
"image2": item.get("mpic"),
"description": item.get("introduce"),
"duration": item.get("duration"),
"tags": tags,
"time": time,
"channel": channel
}
Scheduler.schedule(
AlbumCrawler.type,
source_id,
data,
reset=reset
)
start += 1
def init(conf=None):
if not conf:
conf = {}
for id, channel in CHANNELS.iteritems():
data = {
"channel": channel
}
Scheduler.schedule(
ListCrawler.type,
key=id,
data=data,
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600)
)
def process_album(self, item):
sites = {}
fangying_id = re.findall("f_(.+)\.html", item['link'])[0]
for play in item['plays']:
site = play['site']
if site not in SITES:
continue
if play["url"].find("fangying.com") != -1:
stream = []
else:
format = "thunder" if site == "thunder" else ""
stream = [{"url" : play["url"], "format" : format}]
video = VideoItemModel({
"title" : play["title"],
"url" : play["url"],
"stream" : stream,
})
if not sites.has_key(site):
sites[site] = []
sites[site].append(dict(video))
model = None
for site, videos in sites.iteritems():
model = VideoSourceModel({
"source" : self.data['source'],
"source_id" : fangying_id,
"videos" : videos,
"title" : item['title'],
"directors" : item['directors'].split("/"),
"actors" : item['performers'].split("/"),
"description" : item['description'],
'categories' : item['genres'].split("/"),
'region' : item['countries'].split("/")[0],
'duration' : parse_duration(item['duration']),
'image' : item['avatar_middle'],
'score' : float(item['douban_rating']) if item.get('douban_rating') else None,
'url' : item['link'],
'price' : 0.0,
'pubtime' : parse_pubtime(item['release_time']),
'channel' : CHANNELS.get(self.key)
})
export(model)
if model:
Scheduler.schedule(RelationCrawler.type, key = fangying_id, data = {'title' : model['title'], 'url' : model['url']})
def crawl(self):
page = 1
while (True):
url = HOT_LIST % page
video_list = loadurl(url)
if video_list == None:
break
else:
for videoinfo in video_list:
video = videoinfo['video'][0]
video['source'] = SOURCE
Scheduler.schedule(AlbumCrawler.type,
video.get('id'),
data=video)
page += 1
def init(conf=None):
if not conf:
conf = {}
data = api_channel(pcode, version)
for channel in data['body']['channel']:
cid = channel.get("cid")
channel_name = channel.get("name")
crawl_data = {
"channel_id": cid,
"channel_name": channel_name,
}
Scheduler.schedule(ListCrawler.type,
key=cid,
data=crawl_data,
priority=conf.get('priority', Priority.High),
interval=conf.get('interval', 3600))
def crawl(self):
type = 3
channel_id = self.key
channel = self.data['channel']
start = 0
num = 16
params = {"order": "times", "time": "today"}
while 1:
list_data = api_list(type, channel_id, start, num, params)
if start == list_data['num']:
return
for item in list_data['data']:
if channel in LONG_VIDEO_CHANNELS.values():
source_id = item['mid']
tags = []
time = item['public_time']
time = datetime.strptime(time, "%Y%m%d")
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get(
"time", datetime.min) if lastdata else datetime.min
reset = time > lasttime
else:
source_id = item['flvid']
tags = item.get("tags").split(",")
time = datetime.utcnow()
reset = False
data = {
"url": item.get("web_url"),
"title": item.get("title"),
"image": item.get("bpic"),
"image2": item.get("mpic"),
"description": item.get("introduce"),
"duration": item.get("duration"),
"tags": tags,
"time": time,
"channel": channel
}
Scheduler.schedule(AlbumCrawler.type,
source_id,
data,
reset=reset)
start += 1
def crawl(self):
page = 1
while(True):
url = HOT_LIST % page
video_list = loadurl(url)
if video_list == None:
break
else:
for videoinfo in video_list:
video = videoinfo['video'][0]
video['source'] = SOURCE
Scheduler.schedule(
AlbumCrawler.type,
video.get('id'),
data = video
)
page+=1
def crawl(self):
for channel in CHANNELS:
list_url=LIST % (DICT.get(channel), 1)#杩涘叆姒滃崟绗竴椤�
pagenum=int(loadurl(list_url).get('pagenum'))
for page in range(pagenum):
page+=1#褰撳墠椤典粠1璁℃暟
current_url=LIST % (DICT.get(channel), page)
lists=loadurl(current_url).get('lists')
for episode in lists:
data={
'title':episode.get('name'),
'image':episode.get('pic'),
'category':episode.get('cate'),
'channel':channel,
'source':SOURCE
}
Scheduler.schedule(
AlbumCrawler.type,
episode.get('mid'),
data,
reset=True
)
def crawl(self):
cid = self.key
channel = CHANNELS[int(cid)]
page = 1
pagesize = 30
while 1:
try:
data = api_shows(cid, page, pagesize)
if data is not None:
page += 1
else:
return
except:
self.logger.warning(get_exception_info())
continue
if not data.get('results'):
break
for item in data['results']:
try:
show_id = item['tid']
reset = (item['completed'] == 0)
data = {
'channel':
channel,
'image':
item.get('show_vthumburl_hd')
if item.get('show_vthumburl_hd') else
item.get('show_thumburl_hd'),
'image2':
item.get('show_thumburl_hd')
}
Scheduler.schedule(AlbumCrawler.type,
key=show_id,
data=data,
reset=reset)
except:
self.logger.warning(get_exception_info())
def crawl(self):
cid = self.data['cid']
current_time = int(time.time())
for album_data in self.get_albums(cid):
try:
album = extract_album(album_data, self.data['source'])
if not album:
continue
checkup_time = time.mktime(album['time'].timetuple())
# can't get video for paid item
if (not album["price"]) and album.get('source_id'):
Scheduler.schedule(
type=AlbumCrawler.type,
key=album['source_id'],
data={"time": album["time"]},
reset=(current_time - checkup_time) < 86400)
except:
self.logger.warning(get_exception_info())
self.data['updated'] = current_time
def crawl(self):
cid = self.data['cid']
current_time = int(time.time())
for album_data in self.get_albums(cid):
try:
album = extract_album(album_data, self.data['source'])
if not album:
continue
checkup_time = time.mktime(album['time'].timetuple())
# can't get video for paid item
if (not album["price"]) and album.get('source_id'):
Scheduler.schedule(
type=AlbumCrawler.type,
key=album['source_id'],
data={"time": album["time"]},
reset=(current_time - checkup_time) < 86400
)
except:
self.logger.warning(get_exception_info())
self.data['updated'] = current_time
def schedule(request):
response = {}
type = request.GET.get("type")
nextrun = request.GET.get("nextrun")
if type.endswith("album"):
response['error_info'] = "Type Error."
response['status'] = False
return response
try:
nextrun = datetime.strptime(nextrun, "%Y-%m-%d-%H-%M-%S")
except:
response['error_info'] = "Datetime Error."
response['status'] = False
return response
m = Scheduler.monitor_schedule(type, nextrun)
if m is not None:
response['error_info'] = ""
response['status'] = True
else:
response['error_info'] = "Type Error."
response['status'] = False
return response
分两个爬虫抓取，一个抓取更新榜单，另一个抓取单个视频详情
抓取榜单的爬虫会创建相应的详情爬虫，并传给相应的参数和数据
更新榜单地址: http://bdzy.cc/list/?0-1.html
视频详情地址: http://bdzy.cc/detail/?20808.html
'''
import requests, re, HTMLParser
from datetime import datetime
from scrapy.selector import HtmlXPathSelector
from contentservice.crawler import Crawler, Scheduler, Priority, export
from contentservice.models.video import VideoSourceModel, VideoItemModel
from contentservice.utils.datetimeutil import parse_date
from contentservice.utils.text import split
from contentservice.utils import get_exception_info
'''
重要方法说明
Scheduler.schedule(type, key, priority, data, reset, interval, timeout)
type - 爬虫任务的类型
key - 爬虫任务在该类型中的唯一标识（type和key组合起来唯一标识所爬取的内容，key通常为源站id）
priority - 任务优先级 High, Normal, Low
data - 附加数据（用来持久化跟该爬虫实例相关的数据），附加数据每次运行完成会自动持久化
reset - 是否强制重新抓取。默认不会重新抓取已经完成的任务
interval - 任务循环运行的间隔时间，0为只运行一次，默认值为0
timeout - 超时时间，超时会自动杀死任务
Crawler
爬虫基类，每类爬虫都需要继承这个类
方法:
init(conf=None) 初始化（每次程序启动调用一次），用于创建起始爬虫任务
crawl() 爬取代码的主函数
def process_album(self, item):
sites = {}
fangying_id = re.findall("f_(.+)\.html", item['link'])[0]
for play in item['plays']:
site = play['site']
if site not in SITES:
continue
if play["url"].find("fangying.com") != -1:
stream = []
else:
format = "thunder" if site == "thunder" else ""
stream = [{"url": play["url"], "format": format}]
video = VideoItemModel({
"title": play["title"],
"url": play["url"],
"stream": stream,
})
if not sites.has_key(site):
sites[site] = []
sites[site].append(dict(video))
model = None
for site, videos in sites.iteritems():
model = VideoSourceModel({
"source":
self.data['source'],
"source_id":
fangying_id,
"videos":
videos,
"title":
item['title'],
"directors":
item['directors'].split("/"),
"actors":
item['performers'].split("/"),
"description":
item['description'],
'categories':
item['genres'].split("/"),
'region':
item['countries'].split("/")[0],
'duration':
parse_duration(item['duration']),
'image':
item['avatar_middle'],
'score':
float(item['douban_rating'])
if item.get('douban_rating') else None,
'url':
item['link'],
'price':
0.0,
'pubtime':
parse_pubtime(item['release_time']),
'channel':
CHANNELS.get(self.key)
})
export(model)
if model:
Scheduler.schedule(RelationCrawler.type,
key=fangying_id,
data={
'title': model['title'],
'url': model['url']
})
def crawl(self):
min_time = self.data['updated'] #上次爬取到最新视频的更新时间, 为本次爬取的时间下界
max_time = None #本次抓取的最新视频的时间
page = 1
while True:
url = "http://bdzy.cc/list/?0-%s.html" % page
hxs = load_html(url) #读取网页html, 返回一个HtmlXPathSelector
time = None
for s in hxs.select("//body/.//tr[@class='row']"): #用xpath解析html
try:
href = s.select("td[1]/a/@href").extract()[0]
source_id = re.findall("(\d+)\.html", href)[0] #源站ID
title = clean_title(s.select("td[1]/.//text()").extract()[0])
region = s.select("td[2]/.//text()").extract()[0].replace(u"地区", u"")
category = s.select("td[3]/.//text()").extract()[0]
time = s.select("td[4]/.//text()").extract()[0]
time = datetime.strptime(time, "%Y-%m-%d")
if not max_time: #第一条是最新更新的
max_time = time
if time < min_time: #已经爬取到上次最新的数据
break
data = { #详情页爬虫任务的附加数据
"title" : title,
"time" : time,
"category" : category,
"region" : region,
}
#获取对应详情页爬虫的附加数据，用time字段判断该内容是否已经更新，需要重新抓取. 如果第一次创建，则数据为空
lastdata = Scheduler.get_data(AlbumCrawler.type, source_id)
lasttime = lastdata.get("time", datetime.min) if lastdata else datetime.min
#创建相应的专辑爬虫，爬取相应的详情页. key为源站id
Scheduler.schedule(
AlbumCrawler.type,
source_id,
data,
reset = data["time"] > lasttime #是否需要强制重新抓取
)
except:
self.logger.warning(get_exception_info()) #纪录错误信息并继续
continue
if time and time < min_time: #已经爬取到上次最新的数据
break
#获取总页数
text = hxs.select("//div[@class='pages']/span/text()").extract()[0]
page_count = int(re.findall(u"\d+/(\d+)页", text)[0])
#超过总页数
if page >= page_count:
break
page += 1
if max_time:
self.data = {'updated' : max_time} #保存上次爬取到的最新的时间
def crawl(self):
channel_id = self.key
channel = self.data['c_name']
list_params = self.data['c_list_param']
page = list_params['page']
pagesize = 24
now = int(time.time())
params = dict(list_params) # list_params & PARAMS_INFO merge
params.update(PARAMS_INFO)
while True:
list_data = api_list(
auto_id=channel_id, page=page, pagesize=pagesize, params=params)
if list_data['returncode'] != 404:
if list_data.get('cover'):
for item in list_data["cover"]:
source_id = item.get("c_cover_id")
pubtime = item.get("c_year")
checkup_time = datetime.strptime(
item['c_checkup_time'], "%Y-%m-%d %H:%M:%S")
checkup_time = time.mktime(checkup_time.timetuple())
data = {
"source_id": source_id,
"title": item.get("c_title"),
"image": item.get("c_pic"),
"actors": item.get("c_actor"),
"directors": item.get("c_director"),
"categories": item.get("c_subtype"),
"channel": channel,
"region": item.get("c_area"),
"pubtime": pubtime,
}
Scheduler.schedule(
type=AlbumCrawler.type,
key=source_id,
data=data,
# checkup time whthin three hours set reset==True
reset=(now - checkup_time) < 10800
)
page += 1
if list_data.get('video'):
for item in list_data["video"]:
source_id = item.get("c_vid")
pubtime = item.get("c_ctime")
data = {
"source_id": source_id,
"title": item.get("c_title"),
"image": item.get("c_pic"),
"channel": channel,
"pubtime": pubtime,
}
Scheduler.schedule(
type=AlbumCrawler.type,
key=source_id,
data=data,
)
page += 1
else:
return
def init(conf = None):
if not conf:
conf = {}
Scheduler.schedule(TopCrawler.type, priority = conf.get('priority', Priority.High), interval = conf.get('interval', 86400))
def init(conf=None):
if not conf:
conf = {}
for catecode in CHANNELS.keys():
Scheduler.schedule(CategoryCrawler.type, key = str(catecode), data = {"catecode" : catecode}, priority = conf.get('priority', Priority.Normal), interval = conf.get('interval', 3600))
def init(conf=None):
if not conf:
conf = {}
for id in _CHANNEL_DCT.iterkeys():
Scheduler.schedule(CategoryCrawler.type, key=str(id), data={"cid": id}, priority=conf.get(
'priority', Priority.High), interval=conf.get('interval', 3600))
def init(conf=None):
if not conf:
conf = {}
for channel in CHANNELS.iterkeys():
Scheduler.schedule(HistoryCrawler.type, key = channel, data = {"year" : 1900}, priority = conf.get('priority', Priority.Normal), interval = conf.get('interval',86400))
def init(conf=None):
if not conf:
conf = {}
for cid in CHANNELS.keys():
Scheduler.schedule(CategoryCrawler.type, key=str(cid), priority=conf.get(
'priority', Priority.High), interval=conf.get('interval', 3600))
