Commit 6267f8ed authored by Renán Sosa Guillen's avatar Renán Sosa Guillen

crawlers

parent 2593f62b
...@@ -11,8 +11,8 @@ TAG_RE = re.compile(r'<[^>]+>') ...@@ -11,8 +11,8 @@ TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text): def remove_tags(text):
return TAG_RE.sub('', text) return TAG_RE.sub('', text)
LOC_RE = re.compile(r'.+?(\d?\d-?[a-zA-Z]+)?\s?\.-\s?') LOC_RE = re.compile(r'.+?(\d{1,2}-?[a-zA-Z]+)?\s?\.-\s?')
DAT_RE = re.compile(r'\s?(\d?\d-?[a-zA-Z]+)?\s?\.-\s?') DAT_RE = re.compile(r'\s?(\d{1,2}-?[a-zA-Z]+)?\s?\.-\s?')
class NoticiasItem(scrapy.Item): class NoticiasItem(scrapy.Item):
......
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