[enh] csv output support

This commit is contained in:
asciimoo 2013-11-15 18:55:18 +01:00
parent 1297d4109d
commit a192438e9a
2 changed files with 46 additions and 0 deletions

View File

@ -1,5 +1,8 @@
from HTMLParser import HTMLParser from HTMLParser import HTMLParser
import htmlentitydefs import htmlentitydefs
import csv
import codecs
import cStringIO
class HTMLTextExtractor(HTMLParser): class HTMLTextExtractor(HTMLParser):
def __init__(self): def __init__(self):
@ -24,3 +27,33 @@ def html_to_text(html):
s = HTMLTextExtractor() s = HTMLTextExtractor()
s.feed(html) s.feed(html)
return s.get_text() return s.get_text()
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, row):
self.writer.writerow([(s.encode("utf-8").strip() if type(s) == str or type(s) == unicode else str(s)) for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)

View File

@ -26,6 +26,8 @@ from flask import Flask, request, render_template, url_for, Response, make_respo
from searx.engines import search, categories, engines, get_engines_stats from searx.engines import search, categories, engines, get_engines_stats
from searx import settings from searx import settings
import json import json
import cStringIO
from searx.utils import UnicodeWriter
app = Flask(__name__) app = Flask(__name__)
@ -104,6 +106,17 @@ def index():
result['pretty_url'] = result['url'] result['pretty_url'] = result['url']
if request_data.get('format') == 'json': if request_data.get('format') == 'json':
return Response(json.dumps({'query': query, 'results': results}), mimetype='application/json') return Response(json.dumps({'query': query, 'results': results}), mimetype='application/json')
elif request_data.get('format') == 'csv':
csv = UnicodeWriter(cStringIO.StringIO())
if len(results):
keys = results[0].keys()
csv.writerow(keys)
for row in results:
csv.writerow([row[key] for key in keys])
csv.stream.seek(0)
response = Response(csv.stream.read(), mimetype='application/csv', )
response.headers.add('Content-Disposition', 'attachment;Filename=searx_-_{0}.csv'.format(query))
return response
template = render('results.html' template = render('results.html'
,results=results ,results=results
,q=request_data['q'] ,q=request_data['q']