business-address-scrapper/config.yaml at master · CripterHack/business-address-scrapper · GitHub

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
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
153
154
155
156
157
158
159
# Main configuration file for the web scraper

# Scraper settings
scraper:
  mode: production # Options: development, testing, sandbox, production
  rate_limit: 5 # Requests per second
  max_retries: 3
  chunk_size: 1000
  user_agent: "Business Address Scraper/1.0"
  respect_robots_txt: true
  download_delay: 2
  concurrent_requests: 1

# Output settings
output:
  format: csv # Options: csv, json
  directory: data/output
  filename_pattern: "business_data_{timestamp}.csv"
  chunk_enabled: true
  chunk_size: 1000
  compress_output: true

# Logging settings
logging:
  level: INFO # Options: DEBUG, INFO, WARNING, ERROR, CRITICAL
  file: logs/scraper.log
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  rotate: true
  max_size: 10485760 # 10MB
  backup_count: 5
  compress: true

# Database settings
database:
  enabled: true
  type: postgresql
  host: db
  port: 5432  # Puerto interno de PostgreSQL
  name: business_scraper
  user: postgres
  password: devpassword123
  pool_size: 5
  max_overflow: 10
  timeout: 30

# Cache settings
cache:
  enabled: true
  type: filesystem # Options: filesystem, redis, memory
  directory: .cache
  expiration: 86400 # 24 hours
  max_size: 1073741824 # 1GB

# Proxy settings
proxy:
  enabled: true
  rotation: true
  check_interval: 300 # 5 minutes
  timeout: 10
  retry_count: 3
  blacklist_time: 3600 # 1 hour

# OCR settings
ocr:
  enabled: true
  engine: tesseract
  language: eng
  config_path: config/tesseract
  timeout: 30
  preprocessing:
    resize: true
    max_size: 1920
    denoise: true
    threshold: true

# LLaMA settings
llama:
  model_path: ${LLAMA_MODEL_PATH}
  max_tokens: 100
  temperature: 0.7
  top_p: 0.9
  context_size: 2048
  batch_size: 8

# API settings
api:
  duckduckgo:
    enabled: true
    region: "us-en"
    safesearch: "moderate"
    timeout: 30
    max_results: 10
    backend: "api"

# Monitoring settings
monitoring:
  enabled: true
  prometheus:
    enabled: true
    port: 8000
  metrics_endpoint: ${METRICS_ENDPOINT}
  alert_email: ${ALERT_EMAIL}
  error_threshold: 100
  stats_interval: 60

# Security settings
security:
  ssl_verify: true
  use_encryption: true
  encryption_key: ${ENCRYPTION_KEY}
  allowed_domains:
    - chamberofcommerce.com
    - fda.gov
    - yelp.com
    - linkedin.com
    - ny.gov
    - nyc.gov
    - mapquest.com
    - yellowpages.com
    - bbb.org
    - bloomberg.com
    - manta.com
    - maps.google.com
    - google.com

# Performance settings
performance:
  max_memory: 1073741824 # 1GB
  max_cpu_percent: 80
  timeout: 300 # 5 minutes
  gc_interval: 3600 # 1 hour

# Error handling
error_handling:
  retry_codes:
    - 429 # Too Many Requests
    - 500 # Internal Server Error
    - 502 # Bad Gateway
    - 503 # Service Unavailable
    - 504 # Gateway Timeout
  notification:
    enabled: true
    threshold: 100
    interval: 3600 # 1 hour
    methods:
      - email
      - log
  fallback:
    enabled: true
    max_attempts: 3
    delay: 60 # 1 minute

# Backup settings
backup:
  enabled: true
  interval: 86400 # 24 hours
  retention: 7 # days
  compress: true
  path: /var/backup/scraper