1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
import scrapy
import sys
import os
import time
from scrapy.crawler import CrawlerProcess, CrawlerRunner
from scrapy import spiderloader
from scrapy.utils.project import get_project_settings
from crochet import setup
from apscheduler.schedulers.background import BackgroundScheduler
from apscheduler.triggers import cron
from database.models import Page, db
import config
def crawl(the_spider="", cron=False):
try:
db.create_tables(Page.__subclasses__())
settings = get_project_settings()
spiders = spiderloader.SpiderLoader.from_settings(settings)
if cron:
setup()
process = CrawlerRunner(settings)
else:
process = CrawlerProcess(settings)
if the_spider == "":
for spider in spiders.list():
if "crawl" in spider:
process.crawl(spider)
elif the_spider in spiders.list():
process.crawl(the_spider)
else:
print("`"+the_spider+"` is not a valid spider.")
print('Valid spider are: ')
for spider in spiders.list():
if "crawl" in spider:
print(" "+spider)
sys.exit(1)
if not cron:
process.start()
except Exception as e:
print("Error:"+str(e))
def update():
try:
settings = get_project_settings()
process = CrawlerProcess(settings)
spiders = spiderloader.SpiderLoader.from_settings(settings)
for spider in spiders.list():
if "update" in spider:
process.crawl(spider)
process.start()
except Exception as e:
print(e)
def cron_scheduling():
try:
db.create_tables(Page.__subclasses__())
scheduler = BackgroundScheduler()
scheduler.add_jobstore('sqlalchemy', url=config.CRON_DB)
variables = ['minute', 'hour', 'month', 'day_of_week', 'crawler', 'id']
with open(config.CRON_CONF) as f:
for line in f:
if not line.startswith('#'):
datas = list(filter(lambda x: x != "", line.rstrip().split(" ")))
cron_table = dict(zip(variables, datas))
scheduler.add_job(crawl, 'cron', args=[cron_table['crawler'], 'cron'], minute=cron_table['minute'], hour=cron_table['hour'], month=cron_table['month'], day_of_week=cron_table['day_of_week'], id=cron_table['id'], replace_existing=True)
print('Press Ctrl+{0} to exit'.format('Break' if os.name == 'nt' else 'C'))
scheduler.start()
while True:
time.sleep(1)
except Exception as e:
print(e)
def show_help():
print("Launch all crawler => "+str(sys.argv[0])+" crawl")
print("Update all page already crawlerd => "+str(sys.argv[0])+" update")
if __name__ == '__main__':
#main()
if len(sys.argv) == 2:
if sys.argv[1] == "crawl":
crawl()
elif sys.argv[1] == "update":
update()
elif sys.argv[1] == "cron":
cron_scheduling()
else:
show_help()
elif len(sys.argv) == 3:
if sys.argv[1] == "crawl":
crawl(sys.argv[2])
else:
show_help()
else:
show_help()
|
