Skip to content

Instantly share code, notes, and snippets.

@Chestermozhao
Last active November 23, 2019 14:35
Show Gist options
  • Save Chestermozhao/4493a6ce2553e8008a44b56741445cbb to your computer and use it in GitHub Desktop.
Save Chestermozhao/4493a6ce2553e8008a44b56741445cbb to your computer and use it in GitHub Desktop.
scrapy_splash har log
# -*- coding: utf-8 -*-
import logging
import sys
# create logger
logger_name = 'scrapy.splash.log'
log = logging.getLogger(logger_name)
log.setLevel(logging.DEBUG)
# set handler
handler = logging.StreamHandler(sys.stdout)
formatter = logging.Formatter('%(asctime)s:%(name)s:%(levelname)s:%(message)s')
handler.setFormatter(formatter)
log.addHandler(handler)
# -*- coding: utf-8 -*-
import json
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from items import SplashTestItem
from logger import log
class SplashSpider(Spider):
name = "splash_har_log"
start_urls = ["https://www.livescore.bet3000.com/"]
def start_requests(self):
splash_args = {
'wait': 6,
'html': 1,
'har': 1
}
for url in self.start_urls:
yield SplashRequest(url, self.parse, endpoint='render.json', args=splash_args)
def parse(self, response):
log.info(str(response.data["har"]))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment