예제 #1
0
def main():
    logging.basicConfig(level=logging.INFO)
    config = Config()
    Register(to_bytes('http://%s:%d' % (config.get('bind_address', '127.0.0.1'), config.getint('http_port', 6800))),
             config.get('register_path', '/scrapyd-cluster/worker'),
             hosts=config.get('zookeeper_hosts', '127.0.0.1:2181'))

    argv[1:1] = ['-n', '-y', join(dirname(scrapyd.__file__), 'txapp.py')]
    run()
예제 #2
0
#Stage 2 Update (Python 3)
from future import standard_library
standard_library.install_aliases()
from builtins import object
import datetime, json
import urllib.request, urllib.parse, http.client
import os
from scrapy.utils.project import get_project_settings
settings = get_project_settings()
from scrapyd.config import Config
scrapyd_config = Config()
scrapyd_port = scrapyd_config.getint('http_port', 6800)
from dynamic_scraper.models import Scraper


class TaskUtils(object):

    conf = {
        "MAX_SPIDER_RUNS_PER_TASK": 10,
        "MAX_CHECKER_RUNS_PER_TASK": 25,
    }

    def _run_spider(self, **kwargs):
        scrapyd_host = os.environ.get('SCRAPYD_HOST', 'localhost')
        scrapyd_port = os.environ.get('SCRAPYD_PORT', '6800')
        param_dict = {
            'project': 'default',
            'spider': kwargs['spider'],
            'id': kwargs['id'],
            'run_type': kwargs['run_type'],
            'do_action': kwargs['do_action']
#Stage 2 Update (Python 3)
from future import standard_library
standard_library.install_aliases()
from builtins import object
import datetime, json
import urllib.request, urllib.parse, http.client
from scrapy.utils.project import get_project_settings
settings = get_project_settings()
from scrapyd.config import Config
scrapyd_config = Config()
scrapyd_port = scrapyd_config.getint('http_port', 6800)
from dynamic_scraper.models import Scraper

class TaskUtils(object):

    conf = {
        "MAX_SPIDER_RUNS_PER_TASK": 10,
        "MAX_CHECKER_RUNS_PER_TASK": 25,
    }


    def _run_spider(self, **kwargs):
        param_dict = {
            'project': 'default',
            'spider': kwargs['spider'],
            'id': kwargs['id'],
            'run_type': kwargs['run_type'],
            'do_action': kwargs['do_action']
        }
        params = urllib.parse.urlencode(param_dict)
        headers = {"Content-type": "application/x-www-form-urlencoded", "Accept": "text/plain"}