[perf] torrents.html, files.html: don't parse and re-format filesize

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(
             {

searx/engines/bt4g.py

@@ -36,14 +36,11 @@ Implementations
 
 """
 
-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('<br>')
-        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',
             }

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)

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(

searx/engines/kickass.py

@@ -11,7 +11,6 @@ from searx.utils import (
     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)
 

searx/engines/nyaa.py

@@ -9,7 +9,6 @@ from lxml import html
 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.'

searx/engines/piratebay.py

@@ -8,7 +8,7 @@ from datetime import datetime
 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)

searx/engines/solidtorrents.py

@@ -14,7 +14,6 @@ from searx.utils import (
     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),

searx/engines/tokyotoshokan.py

@@ -8,7 +8,7 @@ from datetime import datetime
 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:'):

searx/engines/torznab.py

@@ -56,6 +56,7 @@ from urllib.parse import quote
 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),