def _get_configured_scraper(scraper_type, options, metadata):
try:
ScraperClass = get_scraper(options.module, scraper_type)
except ScrapeError as e:
# silence error only when alldata is present
if 'alldata' in options.types and ('no %s scraper found in' % scraper_type) in str(e):
return None
else:
raise e
return ScraperClass(metadata,
output_dir=options.output_dir,
strict_validation=options.strict,
fastmode=options.fastmode)
def _get_configured_scraper(scraper_type, options, metadata):
try:
ScraperClass = get_scraper(options.module, scraper_type)
except ScrapeError as e:
# silence error only when alldata is present
if 'alldata' in options.types and ('no %s scraper found in' % scraper_type) in str(e):
return None
else:
raise e
return ScraperClass(metadata,
output_dir=options.output_dir,
strict_validation=options.strict,
fastmode=options.fastmode)
def _run_scraper(options, metadata):
_clear_scraped_data(options.output_dir, 'bills')
ScraperClass = get_scraper(mod_path, 'bills')
opts = {'output_dir': options.output_dir,
'no_cache': options.no_cache,
'requests_per_minute': options.rpm,
'strict_validation': options.strict,
'retry_attempts': settings.SCRAPELIB_RETRY_ATTEMPTS,
'retry_wait_seconds': settings.SCRAPELIB_RETRY_WAIT_SECONDS,
}
if options.fastmode:
opts['requests_per_minute'] = 0
opts['use_cache_first'] = True
scraper = ScraperClass(metadata, **opts)
print options.session, options.bill_id
scraper.scrape_bill(options.chamber, options.session, options.bill_id)
def _run_scraper(options, metadata):
_clear_scraped_data(options.output_dir, 'bills')
ScraperClass = get_scraper(mod_path, 'bills')
opts = {
'output_dir': options.output_dir,
'no_cache': options.no_cache,
'requests_per_minute': options.rpm,
'strict_validation': options.strict,
'retry_attempts': settings.SCRAPELIB_RETRY_ATTEMPTS,
'retry_wait_seconds': settings.SCRAPELIB_RETRY_WAIT_SECONDS,
}
if options.fastmode:
opts['requests_per_minute'] = 0
opts['use_cache_first'] = True
scraper = ScraperClass(metadata, **opts)
print options.session, options.bill_id
scraper.scrape_bill(options.chamber, options.session, options.bill_id)
def _run_scraper(options, metadata):
_clear_scraped_data(options.output_dir, "bills")
ScraperClass = get_scraper(mod_path, "bills")
opts = {
"output_dir": options.output_dir,
"no_cache": options.no_cache,
"requests_per_minute": options.rpm,
"strict_validation": options.strict,
"retry_attempts": settings.SCRAPELIB_RETRY_ATTEMPTS,
"retry_wait_seconds": settings.SCRAPELIB_RETRY_WAIT_SECONDS,
}
if options.fastmode:
opts["requests_per_minute"] = 0
opts["use_cache_first"] = True
scraper = ScraperClass(metadata, **opts)
print options.session, options.bill_id
scraper.scrape_bill(options.chamber, options.session, options.bill_id)
def _run_scraper(mod_path, state, scraper_type, options, metadata):
"""
state: lower case two letter abbreviation of state
scraper_type: bills, legislators, committees, votes
"""
_clear_scraped_data(options.output_dir, scraper_type)
try:
ScraperClass = get_scraper(mod_path, state, scraper_type)
except ScrapeError as e:
# only re-raise if not alldata
if not options.alldata:
raise e
else:
return
opts = {'output_dir': options.output_dir,
'no_cache': options.no_cache,
'requests_per_minute': options.rpm,
'timeout': options.timeout,
'strict_validation': options.strict,
'retry_attempts': settings.SCRAPELIB_RETRY_ATTEMPTS,
'retry_wait_seconds': settings.SCRAPELIB_RETRY_WAIT_SECONDS,
}
if options.fastmode:
opts['requests_per_minute'] = 0
opts['use_cache_first'] = True
scraper = ScraperClass(metadata, **opts)
# times: the list to iterate over for second scrape param
if scraper_type in ('bills', 'votes', 'events'):
if not options.sessions:
if options.terms:
times = []
for term in options.terms:
scraper.validate_term(term)
for metaterm in metadata['terms']:
if term == metaterm['name']:
times.extend(metaterm['sessions'])
else:
latest_session = metadata['terms'][-1]['sessions'][-1]
print('No session specified, using latest "%s"' %
latest_session)
times = [latest_session]
else:
times = options.sessions
# validate sessions
for time in times:
scraper.validate_session(time)
elif scraper_type in ('legislators', 'committees'):
if not options.terms:
latest_term = metadata['terms'][-1]['name']
print 'No term specified, using latest "%s"' % latest_term
times = [latest_term]
else:
times = options.terms
# validate terms
for time in times:
scraper.validate_term(time)
# run scraper against year/session/term
for time in times:
for chamber in options.chambers:
scraper.scrape(chamber, time)
if scraper_type == 'events' and len(options.chambers) == 2:
scraper.scrape('other', time)
