eulaly
beb5cf461b
Spider fetches ViewComments.cfm?GdocForumID=N with vPerPage=500, generates all page requests from page-1 metadata, and parses each div.Cbox for comment_id, author, date, title, text, reg_title, reg_desc. Handles span-wrapped comment text. Fixes UTF-8/windows-1251 meta-tag encoding mismatch. 9083 items, 15 empty-text (0.17%). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
98 lines
3.0 KiB
Python
98 lines
3.0 KiB
Python
# Scrapy settings for scraper project
|
|
#
|
|
# For simplicity, this file contains only settings considered important or
|
|
# commonly used. You can find more settings consulting the documentation:
|
|
#
|
|
# https://docs.scrapy.org/en/latest/topics/settings.html
|
|
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
|
|
BOT_NAME = "scraper"
|
|
|
|
SPIDER_MODULES = ["scraper.spiders"]
|
|
NEWSPIDER_MODULE = "scraper.spiders"
|
|
|
|
ADDONS = {}
|
|
|
|
|
|
USER_AGENT = "vath-research-scraper/1.0 (public comment analysis; contact: research)"
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = True
|
|
|
|
# Concurrency and throttling settings
|
|
#CONCURRENT_REQUESTS = 16
|
|
CONCURRENT_REQUESTS_PER_DOMAIN = 1
|
|
DOWNLOAD_DELAY = 1
|
|
|
|
# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
#SPIDER_MIDDLEWARES = {
|
|
# "scraper.middlewares.ScraperSpiderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
#DOWNLOADER_MIDDLEWARES = {
|
|
# "scraper.middlewares.ScraperDownloaderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable extensions
|
|
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
|
#EXTENSIONS = {
|
|
# "scrapy.extensions.telnet.TelnetConsole": None,
|
|
#}
|
|
|
|
# Configure item pipelines
|
|
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
|
#ITEM_PIPELINES = {
|
|
# "scraper.pipelines.ScraperPipeline": 300,
|
|
#}
|
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default)
|
|
# See https://docs.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
|
|
|
|
# HTTP cache — enabled during development to avoid re-hitting the server on test runs.
|
|
# Disable (or delete httpcache/) before a production run.
|
|
HTTPCACHE_ENABLED = True
|
|
HTTPCACHE_EXPIRATION_SECS = 86400 # 24 h
|
|
HTTPCACHE_DIR = "httpcache"
|
|
|
|
# Output
|
|
FEEDS = {
|
|
"output/%(name)s_%(time)s.jsonl": {
|
|
"format": "jsonlines",
|
|
"encoding": "utf-8",
|
|
"overwrite": False,
|
|
}
|
|
}
|
|
|
|
# The site declares windows-1251 in a meta tag but sends valid UTF-8 bytes.
|
|
# Force UTF-8 to prevent lxml from re-decoding via the meta charset.
|
|
DEFAULT_RESPONSE_ENCODING = "utf-8"
|
|
|
|
# Set settings whose default value is deprecated to a future-proof value
|
|
FEED_EXPORT_ENCODING = "utf-8"
|