import scrapy
import sys
from scrapy.crawler import CrawlerProcess
from scrapy import spiderloader
from scrapy.utils.project import get_project_settings

from database.models import Page, db

def crawl(the_spider=""):
    try:
        db.create_tables(Page.__subclasses__())
        settings = get_project_settings()
        process = CrawlerProcess(settings)
        spiders = spiderloader.SpiderLoader.from_settings(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)

        process.start()
    except Exception as e:
        print(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 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()
        else:
            show_help()
    elif len(sys.argv) == 3:
        if sys.argv[1] == "crawl":
            crawl(sys.argv[2])
        else:
            show_help()
    else:
        show_help()