|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Scrapy settings for AmazonChecker project |
|
4
|
|
|
# |
|
5
|
|
|
# For simplicity, this file contains only settings considered important or |
|
6
|
|
|
# commonly used. You can find more settings consulting the documentation: |
|
7
|
|
|
# |
|
8
|
|
|
# https://doc.scrapy.org/en/latest/topics/settings.html |
|
9
|
|
|
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html |
|
10
|
|
|
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html |
|
11
|
|
|
|
|
12
|
|
|
BOT_NAME = 'AmazonChecker' |
|
13
|
|
|
|
|
14
|
|
|
SPIDER_MODULES = ['AmazonChecker.spiders'] |
|
15
|
|
|
NEWSPIDER_MODULE = 'AmazonChecker.spiders' |
|
16
|
|
|
|
|
17
|
|
|
|
|
18
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent |
|
19
|
|
|
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36' |
|
20
|
|
|
|
|
21
|
|
|
# Obey robots.txt rules |
|
22
|
|
|
ROBOTSTXT_OBEY = False |
|
23
|
|
|
|
|
24
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16) |
|
25
|
|
|
#CONCURRENT_REQUESTS = 32 |
|
26
|
|
|
|
|
27
|
|
|
# Configure a delay for requests for the same website (default: 0) |
|
28
|
|
|
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay |
|
29
|
|
|
# See also autothrottle settings and docs |
|
30
|
|
|
#DOWNLOAD_DELAY = 3 |
|
31
|
|
|
# The download delay setting will honor only one of: |
|
32
|
|
|
#CONCURRENT_REQUESTS_PER_DOMAIN = 16 |
|
33
|
|
|
#CONCURRENT_REQUESTS_PER_IP = 16 |
|
34
|
|
|
|
|
35
|
|
|
# Disable coAmazonCheckeries (enabled by default) |
|
36
|
|
|
#COAMAZON-CHECKERIES_ENABLED = False |
|
37
|
|
|
|
|
38
|
|
|
# Disable Telnet Console (enabled by default) |
|
39
|
|
|
#TELNETCONSOLE_ENABLED = False |
|
40
|
|
|
|
|
41
|
|
|
# Override the default request headers: |
|
42
|
|
|
#DEFAULT_REQUEST_HEADERS = { |
|
43
|
|
|
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', |
|
44
|
|
|
# 'Accept-Language': 'en', |
|
45
|
|
|
#} |
|
46
|
|
|
|
|
47
|
|
|
# Enable or disable spider middlewares |
|
48
|
|
|
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html |
|
49
|
|
|
#SPIDER_MIDDLEWARES = { |
|
50
|
|
|
# 'AmazonChecker.middlewares.Amazon-checkerSpiderMiddleware': 543, |
|
51
|
|
|
#} |
|
52
|
|
|
|
|
53
|
|
|
# Enable or disable downloader middlewares |
|
54
|
|
|
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html |
|
55
|
|
|
#DOWNLOADER_MIDDLEWARES = { |
|
56
|
|
|
# 'AmazonChecker.middlewares.Amazon-checkerDownloaderMiddleware': 543, |
|
57
|
|
|
#} |
|
58
|
|
|
|
|
59
|
|
|
# Enable or disable extensions |
|
60
|
|
|
# See https://doc.scrapy.org/en/latest/topics/extensions.html |
|
61
|
|
|
#EXTENSIONS = { |
|
62
|
|
|
# 'scrapy.extensions.telnet.TelnetConsole': None, |
|
63
|
|
|
#} |
|
64
|
|
|
|
|
65
|
|
|
# Configure item pipelines |
|
66
|
|
|
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html |
|
67
|
|
|
#ITEM_PIPELINES = { |
|
68
|
|
|
# 'AmazonChecker.pipelines.Amazon-checkerPipeline': 300, |
|
69
|
|
|
#} |
|
70
|
|
|
|
|
71
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default) |
|
72
|
|
|
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html |
|
73
|
|
|
#AUTOTHROTTLE_ENABLED = True |
|
74
|
|
|
# The initial download delay |
|
75
|
|
|
#AUTOTHROTTLE_START_DELAY = 5 |
|
76
|
|
|
# The maximum download delay to be set in case of high latencies |
|
77
|
|
|
#AUTOTHROTTLE_MAX_DELAY = 60 |
|
78
|
|
|
# The average number of requests Scrapy should be sending in parallel to |
|
79
|
|
|
# each remote server |
|
80
|
|
|
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 |
|
81
|
|
|
# Enable showing throttling stats for every response received: |
|
82
|
|
|
#AUTOTHROTTLE_DEBUG = False |
|
83
|
|
|
|
|
84
|
|
|
# Enable and configure HTTP caching (disabled by default) |
|
85
|
|
|
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings |
|
86
|
|
|
#HTTPCACHE_ENABLED = True |
|
87
|
|
|
#HTTPCACHE_EXPIRATION_SECS = 0 |
|
88
|
|
|
#HTTPCACHE_DIR = 'httpcache' |
|
89
|
|
|
#HTTPCACHE_IGNORE_HTTP_CODES = [] |
|
90
|
|
|
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage' |
|
91
|
|
|
|
kangoo13 /
amazon-checker
