def main():
global DASHBOARD
covid_data = load_previous()
previous_case_data = deepcopy(covid_data.get_case_data())
current_case_data, date = check_for_updates()
ci = any(x.lower() == "--ci" for x in sys.argv)
force = any(x.lower() == "--force" for x in sys.argv)
# Only post under the following conditions:
# 1. There is new data from RPI
# - AND -
# 2. there are new positive tests OR new weekly/total numbers reported
# This avoids the bs updates where all RPI does is reset the daily/weekly numbers
if (
force
or current_case_data != previous_case_data
and (
current_case_data[0] != 0
or any(
current_case_data[x] != previous_case_data[x]
for x in range(2, len(current_case_data))
)
)
):
dashboard_url = DASHBOARD
try:
# We don't want to abuse the Wayback Machine in actions
if not ci:
dashboard_url = savepagenow.capture(DASHBOARD, accept_cache=True)
else:
print("Skipping page archive as we are running in CI mode")
except:
print(f"Page archived failed")
traceback.print_exc()
old_rolling = covid_data.get_rolling()
covid_data.update(current_case_data)
post_discord(
covid_data.get_rolling(),
old_rolling,
current_case_data,
previous_case_data,
date,
dashboard_url,
create_graph(covid_data),
)
save(covid_data)
print(
f"Done. Old: {previous_case_data} New: {current_case_data}\n Rolling: {covid_data.get_rolling()}"
)
def archive(url, user_agent, timeout):
try:
archive_url = savepagenow.capture(url)
except savepagenow.api.WaybackRuntimeError as e:
logger_e.info("{} - {}".format(url, e))
return "", "", False
try:
r = requests.get(archive_url,
headers={"User-Agent": user_agent},
timeout=timeout)
except requests.exceptions.RequestException as e:
logger_e.info("{} - {}".format(url, e))
return "", "", False
except:
logger_e.info("{} - {}".format(url, "Unknown error"))
return "", "", False
return r.text, r.url, r.ok
def arquivar_tweets():
print("Arquivando tweets...")
lista_ids = database.recupera_ids_sem_arquivo2()
for par in lista_ids:
url = "https://twitter.com/" + str(par[1]) + "/status/" + str(par[0])
print(url)
try:
url_arquivo = archiveis.capture(url)
database.adiciona_arquivo(par[0], url_arquivo)
except Exception as E:
print(E)
print("Problema no arquivador principal")
try:
url_arquivo = savepagenow.capture(url)
database.adiciona_arquivo(par[0], url_arquivo)
time.sleep(20)
except Exception as E2:
print(E2)
print("Problema no arquivador reserva.")
def archived_url(SourceURL):
"""Get a real-time archived url of the source url."""
archive_url = None
status = "Wait"
iters = 0
while status == "Wait":
iters += 1
try:
archive_url = savepagenow.capture(
SourceURL,
user_agent="User:YouTubeReviewBot on wikimedia commons")
status = "Done"
except Exception as e:
out(
e,
color="red",
)
if iters > 5:
status = "Stop"
return archive_url
def test_robots_error(self):
with self.assertRaises(savepagenow.BlockedByRobots):
savepagenow.capture("http://www.columbiamissourian.com/")
#!/usr/bin/env python3
# Usage: python archiveplease.py file_containing_links
import savepagenow
import sys
import time
linkfile = sys.argv[1]
links = []
with open(linkfile) as infile:
for line in infile:
if line != "\n" and line[0] != "#":
line = line.strip('\n')
links.append(line)
#print(links) # as check
for link in links:
#print(link)
archiveurl = savepagenow.capture(link)
print(archiveurl)
time.sleep(120)
try:
assert btns[0]["onclick"] == btns[1]["onclick"]
except IndexError:
return None
assert btns[0]["onclick"].startswith("self.location='")
return urljoin("https://www.fanfiction.net/", btns[0]["onclick"][15:][:-1])
url = sys.argv[1]
errors = []
while url:
try:
save.capture(url)
except save.api.WaybackRuntimeError:
print(f"Error: {url}")
time.sleep(60)
print("slept")
try:
save.capture(url)
except save.api.WaybackRuntimeError:
errors.append(url)
sys.exit()
else:
print(f"Saved: {url}")
else:
print(f"Saved: {url}")
print("Arquivando tweets...")
while True:
lista_ids = database.recupera_ids_sem_arquivo()
for par in lista_ids:
url = "https://twitter.com/" + str(par[1]) + "/status/" + str(
par[0])
print(url)
try:
url_arquivo = archiveis.capture(url)
database.adiciona_arquivo(par[0], url_arquivo)
except Exception as E:
print(E)
print("Problema no arquivador principal")
try:
url_arquivo = savepagenow.capture(url)
database.adiciona_arquivo(par[0], url_arquivo)
time.sleep(20)
except Exception as E2:
print(E2)
print("Problema no arquivador reserva.")
def arquivar_tweets():
print("Arquivando tweets...")
lista_ids = database.recupera_ids_sem_arquivo2()
for par in lista_ids:
url = "https://twitter.com/" + str(par[1]) + "/status/" + str(par[0])
print(url)
try:
url_arquivo = archiveis.capture(url)
import savepagenow
url_file = open('urls.txt', 'r')
for url in url_file.readlines():
print(url)
savepagenow.capture(url)
archived_url = savepagenow.capture(url)
print(archived_url)
file = open('archived_urls.txt', 'a')
file.write(archived_url)
file.close()
url_file.close()
