Попытка запустить программу очистки веб-страниц, но я получаю сообщение об ошибке «Соединение отклонено другой стороной: 111: Соединение отклонено».Я думаю, что это может иметь какое-то отношение к моему Splash_url, хотя я проверил, что localhost8050 запущен и работает.Потому что, если это не так, то я не знаю, в чем проблема.
setting.py
BOT_NAME = 'scrapy_javascript'
SPIDER_MODULES = ['scrapy_javascript.spiders']
NEWSPIDER_MODULE = 'scrapy_javascript.spiders'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# The path of the csv file that contains the pairs
PROXY_CSV_FILE = "proxies.csv"
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
SPLASH_URL = 'http://localhost:8050'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
SplashSpider.py
import csv
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from ..items import GameItem
# process the csv file so the url + ip address + useragent pairs are the same as defined in the file
# returns a list of dictionaries, example:
# [ {'url': 'http://www.starcitygames.com/catalog/category/Rivals%20of%20Ixalan',
# 'ip': 'http://204.152.114.244:8050',
# 'ua': "Mozilla/5.0 (BlackBerry; U; BlackBerry 9320; en-GB) AppleWebKit/534.11"},
# ...
# ]
def process_csv(csv_file):
data = []
reader = csv.reader(csv_file)
next(reader)
for fields in reader:
if fields[0] != "":
url = fields[0]
else:
continue # skip the whole row if the url column is empty
if fields[1] != "":
ip = "http://" + fields[1] + ":8050" # adding http and port because this is the needed scheme
if fields[2] != "":
useragent = fields[2]
data.append({"url": url, "ip": ip, "ua": useragent})
return data
class MySpider(Spider):
name = 'splash_spider' # Name of Spider
# notice that we don't need to define start_urls
# just make sure to get all the urls you want to scrape inside start_requests function
# getting all the url + ip address + useragent pairs then request them
def start_requests(self):
# get the file path of the csv file that contains the pairs rom the settings.py
with open(self.settings["PROXY_CSV_FILE"], mode="r") as csv_file:
# requests is a list of dictionaries like this -> {url: str, ua: str, ip: str}
requests = process_csv(csv_file)
for req in requests:
# no need to create custom middlewares
# just pass useragent using the headers param, and pass proxy using the meta param
yield SplashRequest(url=req["url"], callback=self.parse, args={"wait": 3},
headers={"User-Agent": req["ua"]},
meta={"proxy": (req["ip"])})
# Scraping
def parse(self, response):
item = GameItem()
for game in response.css("tr"):
# Card Name
item["card_name"] = game.css("a.card_popup::text").extract_first()
yield item
Сообщение об ошибке:
Traceback (most recent call last):
File "/home/trno224/.local/lib/python2.7/site-packages/scrapy/core/downloader/middleware.py", line 43, in process_request
defer.returnValue((yield download_func(request=request,spider=spider)))
ConnectionRefusedError: Connection was refused by other side: 111: Connection refused.
2019-05-28 11:59:44 [scrapy.downloadermiddlewares.retry] DEBUG: Gave up retrying <GET http://www.starcitygames.com/catalog/category/Avacyn%20Restored via http://localhost:8050/render.html> (failed 3 times): Connection was refused by other side: 111: Connection refused.
2019-05-28 11:59:44 [scrapy.downloadermiddlewares.retry] DEBUG: Gave up retrying <GET http://www.starcitygames.com/catalog/category/Commander%202013%20Edition via http://localhost:8050/render.html> (failed 3 times): Connection was refused by other side: 111: Connection refused.
2019-05-28 11:59:44 [scrapy.spidermiddlewares.httperror] INFO: Ignoring response <404 http://www.starcitygames.com/catalog/category/Weatherlight>: HTTP status code is not handled or not allowed
2019-05-28 11:59:44 [scrapy.downloadermiddlewares.retry] DEBUG: Gave up retrying <GET http://www.starcitygames.com/catalog/category/Archenemy%20Nicol%20Bolas via http://localhost:8050/render.html> (failed 3 times): Connection was refused by other side: 111: Connection refused.
2019-05-28 11:59:44 [scrapy.core.engine] DEBUG: Crawled (404) <GET http://www.starcitygames.com/catalog/category/Welcome%20Deck%202016 via http://localhost:8050/render.html> (referer: None)
2019-05-28 11:59:44 [scrapy.core.scraper] ERROR: Error downloading <GET http://www.starcitygames.com/catalog/category/Avacyn%20Restored via http://localhost:8050/render.html>
2019-05-28 21:06:32 [scrapy.core.engine] INFO: Closing spider (finished)
2019-05-28 21:06:32 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/exception_count': 558,
'downloader/exception_type_count/twisted.internet.error.ConnectionRefusedError': 558,
'downloader/request_bytes': 387967,
'downloader/request_count': 560,
'downloader/request_method_count/GET': 2,
'downloader/request_method_count/POST': 558,
'downloader/response_bytes': 1344,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/404': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2019, 5, 29, 1, 6, 32, 860344),
'log_count/DEBUG': 560,
'log_count/ERROR': 186,
'log_count/INFO': 33,
'memusage/max': 58634240,
'memusage/startup': 54370304,
'response_received_count': 2,
'retry/count': 372,
'retry/max_reached': 186,
'retry/reason_count/twisted.internet.error.ConnectionRefusedError': 372,
'robotstxt/request_count': 2,
'robotstxt/response_count': 2,
'robotstxt/response_status_count/200': 1,
'robotstxt/response_status_count/404': 1,
'scheduler/dequeued': 744,
'scheduler/dequeued/memory': 744,
'scheduler/enqueued': 744,
'scheduler/enqueued/memory': 744,
'splash/render.html/request_count': 186,
'start_time': datetime.datetime(2019, 5, 29, 0, 42, 2, 24066)}
2019-05-28 21:06:32 [scrapy.core.engine] INFO: Spider closed (finished)