337bd6d · searx · git.iko.soy

git.iko.soy/searx

simplify datetime extraction

commit337bd6d907503176eb94290c3f386ce88167dea8 authorThomas Pointhuber <thomas.pointhuber@gmx.at> dateTue 18 Mar 2014, 13:19 (13 years ago) parentfd86bf8

5 files changed+15−13

compare with master

unifiedsplit

requirements.txt+1 searx/engines/google_news.py+4−10 searx/engines/yahoo_news.py+2−3 searx/engines/youtube.py+7 setup.py+1

requirements.txt+1

@@ -3,3 +3,4 @@ flask-babel

33grequests

44lxml

55pyyaml

6+python-dateutil

searx/engines/google_news.py+4−10

@@ -2,6 +2,7 @@

33from urllib import urlencode

44from json import loads

5+from dateutil import parser

56from datetime import datetime

78categories = ['news']

@@ -32,16 +33,9 @@ def response(resp):

3233 return []

3334

3435 for result in search_res['responseData']['results']:

35−# S.149 (159), library.pdf

36−# datetime.strptime("Mon, 10 Mar 2014 16:26:15 -0700",

37−# "%a, %d %b %Y %H:%M:%S %z")

38−# publishedDate = parse(result['publishedDate'])

39− publishedDate = datetime.strptime(

40− str.join(' ', result['publishedDate'].split(None)[0:5]),

41− "%a, %d %b %Y %H:%M:%S")

42− #utc_offset = timedelta(result['publishedDate'].split(None)[5])

43− # local = utc + offset

44− #publishedDate = publishedDate + utc_offset

36+

37+# Mon, 10 Mar 2014 16:26:15 -0700

38+ publishedDate = parser.parse(result['publishedDate'])

4539

4640 results.append({'url': result['unescapedUrl'],

4741 'title': result['titleNoFormatting'],

searx/engines/yahoo_news.py+2−3

@@ -6,6 +6,7 @@ from searx.engines.xpath import extract_text, extract_url

66from searx.engines.yahoo import parse_url

77from datetime import datetime, timedelta

88import re

9+from dateutil import parser

910

1011categories = ['news']

1112search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'

@@ -52,9 +53,7 @@ def response(resp):

5253 - timedelta(hours=int(timeNumbers[0]))\

5354 - timedelta(minutes=int(timeNumbers[1]))

5455 else:

55− # TODO year in string possible?

56− publishedDate = datetime.strptime(publishedDate,

57− "%b %d %H:%M%p")

56+ publishedDate =parser.parse(publishedDate)

5857

5958 if publishedDate.year == 1900:

6059 publishedDate = publishedDate.replace(year=datetime.now().year)

searx/engines/youtube.py+7

@@ -1,5 +1,7 @@

11from json import loads

22from urllib import urlencode

3+from dateutil import parser

4+from datetime import datetime

46categories = ['videos']

@@ -35,6 +37,10 @@ def response(resp):

3537 content = ''

3638 thumbnail = ''

3739

40+#"2013-12-31T15:22:51.000Z"

41+ pubdate = result['published']['$t']

42+ publishedDate = parser.parse(pubdate)

43+

3844 if result['media$group']['media$thumbnail']:

3945 thumbnail = result['media$group']['media$thumbnail'][0]['url']

4046 content += '<a href="{0}" title="{0}" ><img src="{1}" /></a>'.format(url, thumbnail) # noqa

@@ -48,6 +54,7 @@ def response(resp):

4854 'title': title,

4955 'content': content,

5056 'template': 'videos.html',

57+ 'publishedDate': publishedDate,

5158 'thumbnail': thumbnail})

5259

5360 return results

setup.py+1

@@ -35,6 +35,7 @@ setup(

3535 'lxml',

3636 'pyyaml',

3737 'setuptools',

38+ 'python-dateutil',

3839 ],

3940 extras_require={

4041 'test': [