Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# -*- coding: utf-8 -*-
import logging
from dotenv import load_dotenv
import os
true_list = ['True', 'true', 'TRUE', 1, '1']
load_dotenv()
# Scrapy settings for tutorial project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'tutorial'
SPIDER_MODULES = ['spiders']
NEWSPIDER_MODULE = 'spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'tutorial (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
# COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
# TELNETCONSOLE_ENABLED = False
# Override the default request headers:
# DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
# }
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# 'tutorial.middlewares.TutorialSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'tutorial.middlewares.TutorialDownloaderMiddleware': 543,
# }
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
# EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
# }
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
IMAGES_STORE = '../image'
ITEM_PIPELINES = {
'pipelines.DatabaseWriter.DatabaseWriter': 101,
'pipelines.StatsMailer.StatsMailer': 999,
'pipelines.StatsWriter.StatsWriter': 1000,
'scrapy.pipelines.images.ImagesPipeline': 1,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
# AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
# HTTPCACHE_ENABLED = True
# HTTPCACHE_EXPIRATION_SECS = 0
# HTTPCACHE_DIR = 'httpcache'
# HTTPCACHE_IGNORE_HTTP_CODES = []
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
CONNECTION_STRING = "{drivername}://{user}:{passwd}@{host}:{port}/{db_name}?charset=utf8".format(
drivername=os.getenv('DB_CONNECTION'),
user=os.getenv('DB_USERNAME'),
passwd=os.getenv('DB_PASSWORD'),
host=os.getenv('DB_HOST'),
port=os.getenv('DB_PORT'),
db_name=os.getenv('DB_DATABASE'),
)
# Logger config
LOG_FILE = os.getenv('LOG_FILE', 'log.log')
LOG_ENABLED = os.getenv('LOG_ENABLED', 'True') in true_list
LOG_LEVEL = logging._nameToLevel.get(os.getenv('LOG_LEVEL', 'INFO'))
LOG_FORMAT = os.getenv('LOG_FORMAT', '%(asctime)s - %(levelname)s - %(name)s : \n %(message)s')
LOG_STDOUT = os.getenv('LOG_STDOUT', 'False') in true_list
LOG_SHORT_NAMES = False
# LOG_DATEFORMAT
# Mail config
MAIL_FROM = os.getenv('MAIL_FROM', 'scrapy@localhost')
MAIL_HOST = os.getenv('MAIL_HOST')
MAIL_PORT = int(os.getenv('MAIL_PORT', 465))
MAIL_USER = os.getenv('MAIL_USER')
MAIL_PASS = os.getenv('MAIL_PASS')
MAIL_TLS = os.getenv('MAIL_TLS', 'False') in true_list
MAIL_SSL = os.getenv('MAIL_SSL', 'True') in true_list