Skip to content

crawlersNoticias
crawlersNoticias
Commit c8ff1f67 authored by Mario Chirinos's avatar Mario Chirinos
Browse files
Options

last date finder

parent 3101d32e
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
scripts/siteCrawler.py
View file @ c8ff1f67
...@@ -45,7 +45,7 @@ def crawlNews(directory, cfg, endDate=datetime.datetime.now()): ...@@ -45,7 +45,7 @@ def crawlNews(directory, cfg, endDate=datetime.datetime.now()):
startDate=datetime.datetime.strptime(cfg["startDate"], '%Y-%m-%d') startDate=datetime.datetime.strptime(cfg["startDate"], '%Y-%m-%d')
delta = endDate-startDate delta = endDate-startDate
return 0
for i in range(delta.days + 1): for i in range(delta.days + 1):
day = startDate + datetime.timedelta(days=i) day = startDate + datetime.timedelta(days=i)
yeardir = directory+str(day.year)+"/" yeardir = directory+str(day.year)+"/"
...@@ -68,7 +68,6 @@ def main(argv): ...@@ -68,7 +68,6 @@ def main(argv):
with open(argv[1]+'settings.json') as json_file: with open(argv[1]+'settings.json') as json_file:
cfg = json.load(json_file) cfg = json.load(json_file)
print(cfg) print(cfg)
return 0
if len(argv)==2: if len(argv)==2:
crawlNews(argv[1], cfg) crawlNews(argv[1], cfg)
if len(argv)==3: if len(argv)==3:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment