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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
|
# File 'lib/kimurai/base.rb', line 100
def self.crawl!(exception_on_fail: true)
logger.error "Spider: already running: #{name}" and return false if running?
@storage = Storage.new
@savers = {}
@update_mutex = Mutex.new
@run_info = {
spider_name: name, status: :running, error: nil, environment: Kimurai.env,
start_time: Time.new, stop_time: nil, running_time: nil,
visits: { requests: 0, responses: 0 }, items: { sent: 0, processed: 0 },
events: { requests_errors: Hash.new(0), drop_items_errors: Hash.new(0), custom: Hash.new(0) }
}
logger.info "Spider: started: #{name}"
open_spider if self.respond_to? :open_spider
spider = self.new
spider.with_info = true
if start_urls
start_urls.each do |start_url|
if start_url.class == Hash
spider.request_to(:parse, start_url)
else
spider.request_to(:parse, url: start_url)
end
end
else
spider.parse
end
rescue StandardError, SignalException, SystemExit => e
@run_info.merge!(status: :failed, error: e.inspect)
exception_on_fail ? raise(e) : [@run_info, e]
else
@run_info.merge!(status: :completed)
ensure
if spider
spider.browser.destroy_driver! if spider.instance_variable_get("@browser")
stop_time = Time.now
total_time = (stop_time - @run_info[:start_time]).round(3)
@run_info.merge!(stop_time: stop_time, running_time: total_time)
close_spider if self.respond_to? :close_spider
message = "Spider: stopped: #{@run_info.merge(running_time: @run_info[:running_time]&.duration)}"
failed? ? logger.fatal(message) : logger.info(message)
@run_info, @storage, @savers, @update_mutex = nil
end
end
|