def get_html(d_url, p_url, c_t):
global cache_currentTime
t = time()
if (p_url in cache_dict) and (t - cache_currentTime < c_t):
print(
f"Returned {p_url} from cache. Cached time:{t-cache_currentTime} "
)
return cache_dict[p_url]
browser = get_driver(d_url)
if connect_to_site(browser, p_url):
print(f"Get page {p_url}")
html = browser.page_source
cache_dict[p_url] = html
cache_currentTime = t
browser.quit()
return html
else:
print('Error connecting to [p_url]')
browser.quit()
return None
def run_process(page_number, filename):
browser = get_driver()
if connect_to_base(browser, page_number):
sleep(2)
html = browser.page_source
output_list = parse_html(html)
write_to_file(output_list, filename)
browser.quit()
else:
print('Error connecting to hackernews')
browser.quit()
def run_process(page_number, filename, headless):
# init browser
browser = get_driver(headless)
if connect_to_base(browser, page_number):
sleep(2)
html = browser.page_source
output_list = parse_html(html)
write_to_file(output_list, filename)
# exit
browser.quit()
else:
print("Error connecting to hackernews")
browser.quit()
output_list = parse_html(html)
########
# here #
########
write_to_file(output_list, filename)
else:
print('Error connecting to hackernews')
if __name__ == '__main__':
# set variables
start_time = time()
current_page = 1
output_timestamp = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
output_filename = f'output_{output_timestamp}.csv'
browser = get_driver()
# scrape and crawl
while current_page <= 20:
print(f'Scraping page #{current_page}...')
run_process(current_page, output_filename, browser)
########
# here #
########
current_page = current_page + 1
# exit
browser.quit()
end_time = time()
elapsed_time = end_time - start_time
print(f'Elapsed run time: {elapsed_time} seconds')
import sys
from time import sleep
from scrapers.scraper import get_driver, connect_to_base, parse_html
def run_process(rowser):
if connect_to_base(browser):
print(f'Scraping random Wikipedia page...')
sleep(2)
html = browser.page_source
return parse_html(html)
else:
print("Error connecting to Wikipedia")
return False
if __name__ == '__main__':
browser = get_driver(sys.argv[1])
data = run_process(browser)
print(data)
browser.quit()
print(f'Finished!')
def test_brower(self):
browser=get_driver(self.driver_url)
self.assertTrue(browser is not None)
if __name__ == "__main__":
# headless mode?
headless = False
if len(sys.argv) > 1:
if sys.argv[1] == "headless":
print("Running in headless mode")
headless = True
# set variables
start_time = time()
current_page = 1
output_timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
output_filename = f"output_{output_timestamp}.csv"
# init browser
browser = get_driver(headless=headless)
# scrape and crawl
while current_page <= 20:
print(f"Scraping page #{current_page}...")
run_process(current_page, output_filename, browser)
current_page = current_page + 1
# exit
browser.quit()
end_time = time()
elapsed_time = end_time - start_time
print(f"Elapsed run time: {elapsed_time} seconds")
