Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 16bdc0ba authored by Adam Tauber's avatar Adam Tauber
Browse files

[mod] do not escape html content in engines

parent 28f12ef5

searx/engines/archlinux.py

+1 −2
Original line number Diff line number Diff line
@@ -12,7 +12,6 @@ 
"""



from urlparse import urljoin

from cgi import escape

from urllib import urlencode

from lxml import html

from searx.engines.xpath import extract_text
@@ -135,7 +134,7 @@ def response(resp): 
    for result in dom.xpath(xpath_results):

        link = result.xpath(xpath_link)[0]

        href = urljoin(base_url, link.attrib.get('href'))

        title = escape(extract_text(link))

        title = extract_text(link)



        results.append({'url': href,

                        'title': title})

searx/engines/base.py

+1 −2
Original line number Diff line number Diff line
@@ -16,7 +16,6 @@ 
from lxml import etree

from urllib import urlencode

from searx.utils import searx_useragent

from cgi import escape

from datetime import datetime

import re
@@ -94,7 +93,7 @@ def response(resp): 
                url = item.text



            elif item.attrib["name"] == "dcdescription":

                content = escape(item.text[:300])

                content = item.text[:300]

                if len(item.text) > 300:

                    content += "..."

searx/engines/bing.py

+2 −3
Original line number Diff line number Diff line
@@ -14,7 +14,6 @@ 
"""



from urllib import urlencode

from cgi import escape

from lxml import html

from searx.engines.xpath import extract_text
@@ -61,7 +60,7 @@ def response(resp): 
        link = result.xpath('.//h3/a')[0]

        url = link.attrib.get('href')

        title = extract_text(link)

        content = escape(extract_text(result.xpath('.//p')))

        content = extract_text(result.xpath('.//p'))



        # append result

        results.append({'url': url,
@@ -73,7 +72,7 @@ def response(resp): 
        link = result.xpath('.//h2/a')[0]

        url = link.attrib.get('href')

        title = extract_text(link)

        content = escape(extract_text(result.xpath('.//p')))

        content = extract_text(result.xpath('.//p'))



        # append result

        results.append({'url': url,

searx/engines/btdigg.py

+2 −3
Original line number Diff line number Diff line
@@ -11,7 +11,6 @@ 
"""



from urlparse import urljoin

from cgi import escape

from urllib import quote

from lxml import html

from operator import itemgetter
@@ -51,8 +50,8 @@ def response(resp): 
    for result in search_res:

        link = result.xpath('.//td[@class="torrent_name"]//a')[0]

        href = urljoin(url, link.attrib.get('href'))

        title = escape(extract_text(link))

        content = escape(extract_text(result.xpath('.//pre[@class="snippet"]')[0]))

        title = extract_text(link)

        content = extract_text(result.xpath('.//pre[@class="snippet"]')[0])

        content = "<br />".join(content.split("\n"))



        filesize = result.xpath('.//span[@class="attr_val"]/text()')[0].split()[0]

searx/engines/dailymotion.py

+1 −2
Original line number Diff line number Diff line
@@ -14,7 +14,6 @@ 


from urllib import urlencode

from json import loads

from cgi import escape

from datetime import datetime



# engine dependent config
@@ -57,7 +56,7 @@ def response(resp): 
    for res in search_res['list']:

        title = res['title']

        url = res['url']

        content = escape(res['description'])

        content = res['description']

        thumbnail = res['thumbnail_360_url']

        publishedDate = datetime.fromtimestamp(res['created_time'], None)

        embedded = embedded_url.format(videoid=res['id'])