diff --git a/searx/engines/1337x.py b/searx/engines/1337x.py
index 22129750332..f9a0d0412aa 100644
--- a/searx/engines/1337x.py
+++ b/searx/engines/1337x.py
@@ -6,7 +6,7 @@
from urllib.parse import quote, urljoin
from lxml import html
-from searx.utils import extract_text, get_torrent_size, eval_xpath, eval_xpath_list, eval_xpath_getindex
+from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex
# about
about = {
@@ -40,9 +40,7 @@ def response(resp):
title = extract_text(eval_xpath(result, './td[contains(@class, "name")]/a[2]'))
seed = extract_text(eval_xpath(result, './/td[contains(@class, "seeds")]'))
leech = extract_text(eval_xpath(result, './/td[contains(@class, "leeches")]'))
- filesize_info = extract_text(eval_xpath(result, './/td[contains(@class, "size")]/text()'))
- filesize, filesize_multiplier = filesize_info.split()
- filesize = get_torrent_size(filesize, filesize_multiplier)
+ filesize = extract_text(eval_xpath(result, './/td[contains(@class, "size")]/text()'))
results.append(
{
diff --git a/searx/engines/bt4g.py b/searx/engines/bt4g.py
index 98a8c308773..a468124fe16 100644
--- a/searx/engines/bt4g.py
+++ b/searx/engines/bt4g.py
@@ -36,14 +36,11 @@
"""
-import re
from datetime import datetime
from urllib.parse import quote
from lxml import etree
-from searx.utils import get_torrent_size
-
# about
about = {
"website": 'https://bt4gprx.com',
@@ -103,8 +100,6 @@ def response(resp):
title = entry.find("title").text
link = entry.find("guid").text
fullDescription = entry.find("description").text.split('
')
- filesize = fullDescription[1]
- filesizeParsed = re.split(r"([A-Z]+)", filesize)
magnetlink = entry.find("link").text
pubDate = entry.find("pubDate").text
results.append(
@@ -114,7 +109,7 @@ def response(resp):
'magnetlink': magnetlink,
'seed': 'N/A',
'leech': 'N/A',
- 'filesize': get_torrent_size(filesizeParsed[0], filesizeParsed[1]),
+ 'filesize': fullDescription[1],
'publishedDate': datetime.strptime(pubDate, '%a,%d %b %Y %H:%M:%S %z'),
'template': 'torrent.html',
}
diff --git a/searx/engines/btdigg.py b/searx/engines/btdigg.py
index 588d62093e8..19378518212 100644
--- a/searx/engines/btdigg.py
+++ b/searx/engines/btdigg.py
@@ -6,7 +6,7 @@
from urllib.parse import quote, urljoin
from lxml import html
-from searx.utils import extract_text, get_torrent_size
+from searx.utils import extract_text
# about
about = {
@@ -58,13 +58,9 @@ def response(resp):
content = content.strip().replace('\n', ' | ')
content = ' '.join(content.split())
- filesize = result.xpath('.//span[@class="torrent_size"]/text()')[0].split()[0]
- filesize_multiplier = result.xpath('.//span[@class="torrent_size"]/text()')[0].split()[1]
+ filesize = result.xpath('.//span[@class="torrent_size"]/text()')[0]
files = (result.xpath('.//span[@class="torrent_files"]/text()') or ['1'])[0]
- # convert filesize to byte if possible
- filesize = get_torrent_size(filesize, filesize_multiplier)
-
# convert files to int if possible
try:
files = int(files)
diff --git a/searx/engines/digbt.py b/searx/engines/digbt.py
index ae78f1a9e6e..fd3d1fb1691 100644
--- a/searx/engines/digbt.py
+++ b/searx/engines/digbt.py
@@ -5,7 +5,7 @@
from urllib.parse import urljoin
from lxml import html
-from searx.utils import extract_text, get_torrent_size
+from searx.utils import extract_text
# about
about = {
@@ -45,7 +45,7 @@ def response(resp):
title = extract_text(result.xpath('.//a[@title]'))
content = extract_text(result.xpath('.//div[@class="files"]'))
files_data = extract_text(result.xpath('.//div[@class="tail"]')).split()
- filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER])
+ filesize = f"{files_data[FILESIZE]} {files_data[FILESIZE_MULTIPLIER]}"
magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0]
results.append(
diff --git a/searx/engines/kickass.py b/searx/engines/kickass.py
index 12bf9c04d43..311c2885baa 100644
--- a/searx/engines/kickass.py
+++ b/searx/engines/kickass.py
@@ -11,7 +11,6 @@
eval_xpath_getindex,
eval_xpath_list,
extract_text,
- get_torrent_size,
int_or_zero,
)
@@ -54,7 +53,7 @@ def response(resp):
result['content'] = extract_text(eval_xpath(tag, './/span[@class="font11px lightgrey block"]'))
result['seed'] = int_or_zero(extract_text(eval_xpath(tag, './/td[contains(@class, "green")]')))
result['leech'] = int_or_zero(extract_text(eval_xpath(tag, './/td[contains(@class, "red")]')))
- result['filesize'] = get_torrent_size(*extract_text(eval_xpath(tag, './/td[contains(@class, "nobr")]')).split())
+ result['filesize'] = extract_text(eval_xpath(tag, './/td[contains(@class, "nobr")]'))
results.append(result)
diff --git a/searx/engines/nyaa.py b/searx/engines/nyaa.py
index c22339dbf55..f3862f503b6 100644
--- a/searx/engines/nyaa.py
+++ b/searx/engines/nyaa.py
@@ -9,7 +9,6 @@
from searx.utils import (
eval_xpath_getindex,
extract_text,
- get_torrent_size,
int_or_zero,
)
@@ -99,11 +98,7 @@ def response(resp):
# let's try to calculate the torrent size
- filesize = None
- filesize_info = eval_xpath_getindex(result, xpath_filesize, 0, '')
- if filesize_info:
- filesize_info = result.xpath(xpath_filesize)[0]
- filesize = get_torrent_size(*filesize_info.split())
+ filesize = eval_xpath_getindex(result, xpath_filesize, 0, '')
# content string contains all information not included into template
content = 'Category: "{category}". Downloaded {downloads} times.'
diff --git a/searx/engines/piratebay.py b/searx/engines/piratebay.py
index ba58e64fcf0..e1f3f611a51 100644
--- a/searx/engines/piratebay.py
+++ b/searx/engines/piratebay.py
@@ -8,7 +8,7 @@
from operator import itemgetter
from urllib.parse import quote
-from searx.utils import get_torrent_size
+from searx.utils import humanize_bytes
# about
about = {
@@ -80,17 +80,12 @@ def response(resp):
# extract and convert creation date
try:
- date = datetime.fromtimestamp(float(result["added"]))
- params['publishedDate'] = date
+ params['publishedDate'] = datetime.fromtimestamp(float(result["added"]))
except: # pylint: disable=bare-except
pass
# let's try to calculate the torrent size
- try:
- filesize = get_torrent_size(result["size"], "B")
- params['filesize'] = filesize
- except: # pylint: disable=bare-except
- pass
+ params['filesize'] = humanize_bytes(int(result["size"]))
# append result
results.append(params)
diff --git a/searx/engines/solidtorrents.py b/searx/engines/solidtorrents.py
index 3cad8e5495d..c2f7e435e75 100644
--- a/searx/engines/solidtorrents.py
+++ b/searx/engines/solidtorrents.py
@@ -14,7 +14,6 @@
eval_xpath,
eval_xpath_getindex,
eval_xpath_list,
- get_torrent_size,
)
about = {
@@ -63,7 +62,7 @@ def response(resp):
'leech': extract_text(stats[2]),
'title': extract_text(title),
'url': resp.search_params['base_url'] + url,
- 'filesize': get_torrent_size(*extract_text(stats[1]).split()),
+ 'filesize': extract_text(stats[1]),
'magnetlink': magnet,
'torrentfile': torrentfile,
'metadata': extract_text(categ),
diff --git a/searx/engines/tokyotoshokan.py b/searx/engines/tokyotoshokan.py
index 33f03642885..ad0be1985ac 100644
--- a/searx/engines/tokyotoshokan.py
+++ b/searx/engines/tokyotoshokan.py
@@ -8,7 +8,7 @@
from urllib.parse import urlencode
from lxml import html
-from searx.utils import extract_text, get_torrent_size, int_or_zero
+from searx.utils import extract_text, int_or_zero
# about
about = {
@@ -49,7 +49,7 @@ def response(resp):
return []
# regular expression for parsing torrent size strings
- size_re = re.compile(r'Size:\s*([\d.]+)(TB|GB|MB|B)', re.IGNORECASE)
+ size_re = re.compile(r'[\d.]+(T|G|M)?B', re.IGNORECASE)
# processing the results, two rows at a time
for i in range(0, len(rows), 2):
@@ -73,9 +73,7 @@ def response(resp):
item = item.strip()
if item.startswith('Size:'):
try:
- # ('1.228', 'GB')
- groups = size_re.match(item).groups()
- params['filesize'] = get_torrent_size(groups[0], groups[1])
+ params['filesize'] = size_re.search(item).group()
except: # pylint: disable=bare-except
pass
elif item.startswith('Date:'):
diff --git a/searx/engines/torznab.py b/searx/engines/torznab.py
index 70ba78ab476..cfe7e2b4f2e 100644
--- a/searx/engines/torznab.py
+++ b/searx/engines/torznab.py
@@ -56,6 +56,7 @@
from lxml import etree # type: ignore
from searx.exceptions import SearxEngineAPIException
+from searx.utils import humanize_bytes
if TYPE_CHECKING:
import httpx
@@ -137,11 +138,9 @@ def build_result(item: etree.Element) -> Dict[str, Any]:
if enclosure is not None:
enclosure_url = enclosure.get('url')
- size = get_attribute(item, 'size')
- if not size and enclosure:
- size = enclosure.get('length')
- if size:
- size = int(size)
+ filesize = get_attribute(item, 'size')
+ if not filesize and enclosure:
+ filesize = enclosure.get('length')
guid = get_attribute(item, 'guid')
comments = get_attribute(item, 'comments')
@@ -154,7 +153,7 @@ def build_result(item: etree.Element) -> Dict[str, Any]:
result: Dict[str, Any] = {
'template': 'torrent.html',
'title': get_attribute(item, 'title'),
- 'filesize': size,
+ 'filesize': humanize_bytes(int(filesize)) if filesize else None,
'files': get_attribute(item, 'files'),
'seed': seeders,
'leech': _map_leechers(leechers, seeders, peers),
diff --git a/searx/templates/simple/result_templates/files.html b/searx/templates/simple/result_templates/files.html
index 0a1424da6f1..01dfc3535a9 100644
--- a/searx/templates/simple/result_templates/files.html
+++ b/searx/templates/simple/result_templates/files.html
@@ -35,14 +35,7 @@
{%- if result.filename %}| {{ _('Filename') }} | {{ result.filename|safe }} |
{% endif -%}
-{%- if result.size %}| {{ _('Filesize') }} |
- {%- if result.size < 1024 %}{{ result.size }} {{ _('Bytes') -}}
- {%- elif result.size < 1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024) }} {{ _('kiB') -}}
- {%- elif result.size < 1024*1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024/1024) }} {{ _('MiB') -}}
- {%- elif result.size < 1024*1024*1024*1024 %}{{ '{0:0.2f}'.format(result.size/1024/1024/1024) }} {{ _('GiB') -}}
- {%- else %}{{ '{0:0.2f}'.format(result.size/1024/1024/1024/1024) }} {{ _('TiB') }}{% endif -%}
- |
-{%- endif -%}
+{%- if result.size %}| {{ _('Filesize') }} | {{ result.size|safe }} |
{%- endif -%}
{%- if result.time %}| {{ _('Date') }} | {{ result.time|safe }} |
{% endif -%}
diff --git a/searx/templates/simple/result_templates/torrent.html b/searx/templates/simple/result_templates/torrent.html
index 46cde2a6519..befad2c89be 100644
--- a/searx/templates/simple/result_templates/torrent.html
+++ b/searx/templates/simple/result_templates/torrent.html
@@ -8,14 +8,7 @@
{% if result.seed is defined %} • {{ icon_big('arrow-swap') }} {{ _('Seeder') }} {{ result.seed }} • {{ _('Leecher') }} {{ result.leech }}
{% endif %}
-{%- if result.filesize %}{{ icon_big('floppy-disk') }} {{ _('Filesize') }}
- {%- if result.filesize < 1024 %}{{ result.filesize }} {{ _('Bytes') }}
- {%- elif result.filesize < 1024*1024 %}{{ '{0:0.2f}'.format(result.filesize/1024) }} {{ _('kiB') }}
- {%- elif result.filesize < 1024*1024*1024 %}{{ '{0:0.2f}'.format(result.filesize/1024/1024) }} {{ _('MiB') }}
- {%- elif result.filesize < 1024*1024*1024*1024 %}{{ '{0:0.2f}'.format(result.filesize/1024/1024/1024) }} {{ _('GiB') }}
- {%- else %}{{ '{0:0.2f}'.format(result.filesize/1024/1024/1024/1024) }} {{ _('TiB') }}{% endif -%}
-
-{%- endif -%}
+{%- if result.filesize %}{{ icon_big('floppy-disk') }} {{ _('Filesize') }}{{ result.filesize }}
{%- endif -%}
{%- if result.files %}{{ icon_big('file') }} {{ _('Number of Files') }} {{ result.files }}
{% endif -%}
diff --git a/searx/utils.py b/searx/utils.py
index 58ff72bb9eb..0c11ccc655a 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -332,29 +332,6 @@ def dict_subset(dictionary: MutableMapping, properties: Set[str]) -> Dict:
return {k: dictionary[k] for k in properties if k in dictionary}
-def get_torrent_size(filesize: str, filesize_multiplier: str) -> Optional[int]:
- """
-
- Args:
- * filesize (str): size
- * filesize_multiplier (str): TB, GB, .... TiB, GiB...
-
- Returns:
- * int: number of bytes
-
- Example:
- >>> get_torrent_size('5', 'GB')
- 5368709120
- >>> get_torrent_size('3.14', 'MiB')
- 3140000
- """
- try:
- multiplier = _STORAGE_UNIT_VALUE.get(filesize_multiplier, 1)
- return int(float(filesize) * multiplier)
- except ValueError:
- return None
-
-
def humanize_bytes(size, precision=2):
"""Determine the *human readable* value of bytes on 1024 base (1KB=1024B)."""
s = ['B ', 'KB', 'MB', 'GB', 'TB']