change mysql address to homeserver
This commit is contained in:
parent
63df475acd
commit
8ad777362e
|
@ -6,106 +6,11 @@
|
||||||
from scrapy import signals
|
from scrapy import signals
|
||||||
|
|
||||||
# useful for handling different item types with a single interface
|
# useful for handling different item types with a single interface
|
||||||
from itemadapter import is_item, ItemAdapter
|
|
||||||
from .myutils import ProxyPool
|
from .myutils import ProxyPool
|
||||||
from .settings import USERNAME, PASSWORD
|
from .settings import USERNAME, PASSWORD
|
||||||
from faker import Faker
|
from faker import Faker
|
||||||
|
|
||||||
|
|
||||||
class NewsspiderSpiderMiddleware:
|
|
||||||
# Not all methods need to be defined. If a method is not defined,
|
|
||||||
# scrapy acts as if the spider middleware does not modify the
|
|
||||||
# passed objects.
|
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def from_crawler(cls, crawler):
|
|
||||||
# This method is used by Scrapy to create your spiders.
|
|
||||||
s = cls()
|
|
||||||
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
||||||
return s
|
|
||||||
|
|
||||||
def process_spider_input(self, response, spider):
|
|
||||||
# Called for each response that goes through the spider
|
|
||||||
# middleware and into the spider.
|
|
||||||
|
|
||||||
# Should return None or raise an exception.
|
|
||||||
return None
|
|
||||||
|
|
||||||
def process_spider_output(self, response, result, spider):
|
|
||||||
# Called with the results returned from the Spider, after
|
|
||||||
# it has processed the response.
|
|
||||||
|
|
||||||
# Must return an iterable of Request, or item objects.
|
|
||||||
for i in result:
|
|
||||||
yield i
|
|
||||||
|
|
||||||
def process_spider_exception(self, response, exception, spider):
|
|
||||||
# Called when a spider or process_spider_input() method
|
|
||||||
# (from other spider middleware) raises an exception.
|
|
||||||
|
|
||||||
# Should return either None or an iterable of Request or item objects.
|
|
||||||
pass
|
|
||||||
|
|
||||||
def process_start_requests(self, start_requests, spider):
|
|
||||||
# Called with the start requests of the spider, and works
|
|
||||||
# similarly to the process_spider_output() method, except
|
|
||||||
# that it doesn’t have a response associated.
|
|
||||||
|
|
||||||
# Must return only requests (not items).
|
|
||||||
for r in start_requests:
|
|
||||||
yield r
|
|
||||||
|
|
||||||
def spider_opened(self, spider):
|
|
||||||
spider.logger.info("Spider opened: %s" % spider.name)
|
|
||||||
|
|
||||||
|
|
||||||
class DecspiderDownloaderMiddleware:
|
|
||||||
# Not all methods need to be defined. If a method is not defined,
|
|
||||||
# scrapy acts as if the downloader middleware does not modify the
|
|
||||||
# passed objects.
|
|
||||||
|
|
||||||
@classmethod
|
|
||||||
def from_crawler(cls, crawler):
|
|
||||||
# This method is used by Scrapy to create your spiders.
|
|
||||||
s = cls()
|
|
||||||
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
|
||||||
return s
|
|
||||||
|
|
||||||
def process_request(self, request, spider):
|
|
||||||
# Called for each request that goes through the downloader
|
|
||||||
# middleware.
|
|
||||||
|
|
||||||
# Must either:
|
|
||||||
# - return None: continue processing this request
|
|
||||||
# - or return a Response object
|
|
||||||
# - or return a Request object
|
|
||||||
# - or raise IgnoreRequest: process_exception() methods of
|
|
||||||
# installed downloader middleware will be called
|
|
||||||
return None
|
|
||||||
|
|
||||||
def process_response(self, request, response, spider):
|
|
||||||
# Called with the response returned from the downloader.
|
|
||||||
|
|
||||||
# Must either;
|
|
||||||
# - return a Response object
|
|
||||||
# - return a Request object
|
|
||||||
# - or raise IgnoreRequest
|
|
||||||
return response
|
|
||||||
|
|
||||||
def process_exception(self, request, exception, spider):
|
|
||||||
# Called when a download handler or a process_request()
|
|
||||||
# (from other downloader middleware) raises an exception.
|
|
||||||
|
|
||||||
# Must either:
|
|
||||||
# - return None: continue processing this exception
|
|
||||||
# - return a Response object: stops process_exception() chain
|
|
||||||
# - return a Request object: stops process_exception() chain
|
|
||||||
pass
|
|
||||||
|
|
||||||
def spider_opened(self, spider):
|
|
||||||
spider.logger.info("Spider opened: %s" % spider.name)
|
|
||||||
|
|
||||||
|
|
||||||
class ProxyMiddleware:
|
class ProxyMiddleware:
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
# 初始化代理列表和每个代理的失败计数
|
# 初始化代理列表和每个代理的失败计数
|
||||||
|
|
|
@ -105,8 +105,8 @@ PROXYPOOL_MIN_DURATION = 1
|
||||||
# MySQL Configuration
|
# MySQL Configuration
|
||||||
MYSQL_USERNAME = "root"
|
MYSQL_USERNAME = "root"
|
||||||
MYSQL_PASSWORD = "yGWptA_tX4bZ2q"
|
MYSQL_PASSWORD = "yGWptA_tX4bZ2q"
|
||||||
MYSQL_HOST = "10.18.30.148"
|
MYSQL_HOST = "chenbingyuan.com"
|
||||||
MYSQL_PORT = 3307
|
MYSQL_PORT = 7033
|
||||||
MYSQL_DATABASE = "crawler_data"
|
MYSQL_DATABASE = "crawler_data"
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user