Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
crawlersNoticias
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
4
Issues
4
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
m3
crawlersNoticias
Commits
067f09e9
Commit
067f09e9
authored
Apr 15, 2020
by
Mario Chirinos Colunga
💬
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
noticiero en linea
parent
57f362cd
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
9 additions
and
5 deletions
+9
-5
noticias.py
...por_dia/noticieroLinea/noticieroLinea/spiders/noticias.py
+9
-5
No files found.
descarga_por_dia/noticieroLinea/noticieroLinea/spiders/noticias.py
View file @
067f09e9
...
...
@@ -8,15 +8,18 @@ Noticiero en Línea, Colima
USO:
scrapy crawl noticias --nolog -s filename=2018-01-03.json -a year=2018 -a month=1 -a day=3
"""
from
dateparser
import
parse
TAG_RE
=
re
.
compile
(
r'<[^>]+>'
)
def
remove_tags
(
text
):
return
TAG_RE
.
sub
(
''
,
text
)
LOC_RE
=
re
.
compile
(
r'\A.+?(\d{1,2}[\s-][a-zA-Z]+[\s-]\d{4})?\s?\.\s?-\s?'
,
re
.
S
)
G_RE
=
re
.
compile
(
r'\s?-\s?'
)
E_RE
=
re
.
compile
(
r'\(Con informaci.*?\)\.?'
)
#-------------------------------------------------------------------------------
def
remove_tags
(
text
):
return
TAG_RE
.
sub
(
''
,
text
)
#-------------------------------------------------------------------------------
class
QuotesSpider
(
scrapy
.
Spider
):
name
=
"noticias"
...
...
@@ -44,7 +47,8 @@ class QuotesSpider(scrapy.Spider):
text
=
''
"La fecha obtenida ya incluye formato y zona horaria"
item
[
'date'
]
=
response
.
xpath
(
'//meta[@property="article:published_time"]/@content'
)
.
extract_first
()
date
=
response
.
css
(
"span.entry-meta-date::text"
)
.
get
()
.
lower
()
item
[
'date'
]
=
parse
(
date
,
date_formats
=
[
"
%
d
%
B,
%
Y"
])
.
isoformat
()
#response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
item
[
'title'
]
=
remove_tags
(
response
.
xpath
(
'//h1[@class="entry-title"]'
)
.
extract_first
())
.
strip
()
item
[
'topic'
]
=
response
.
xpath
(
'//*[@class="entry-tags clearfix"]/a/text()'
)
.
extract_first
()
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment