jandieman/searxng
2
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-12-22 19:50:00 +00:00
Code Issues Projects Releases Wiki Activity

[fix] annas archive: engine broken due to site HTML changes

Browse Source 
Apparently the layout of https://annas-archive.org has changed, making changes necessary.

The issue has been reported in #5146, see there for more details.

- closes #5146
This commit is contained in:
Bnyro
2025-08-28 11:06:38 +02:00
committed by Markus Heiser
parent 5ca08c1813
commit f971774773
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
searx/engines/annas_archive.py
View File

@@ -40,6 +40,7 @@ from lxml import html
from searx.utils import extract_text, eval_xpath, eval_xpath_getindex, eval_xpath_list from searx.utils import extract_text, eval_xpath, eval_xpath_getindex, eval_xpath_list
from searx.enginelib.traits import EngineTraits from searx.enginelib.traits import EngineTraits
from searx.data import ENGINE_TRAITS from searx.data import ENGINE_TRAITS
from searx.exceptions import SearxEngineXPathException
# about # about
about: Dict[str, Any] = { about: Dict[str, Any] = {
@@ -118,30 +119,29 @@ def response(resp) -> List[Dict[str, Optional[str]]]:
results: List[Dict[str, Optional[str]]] = [] results: List[Dict[str, Optional[str]]] = []
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
for item in eval_xpath_list(dom, '//main//div[contains(@class, "h-[125]")]/a'): # The rendering of the WEB page is strange; positions of Anna's result page
results.append(_get_result(item)) # are enclosed in SGML comments. These comments are *uncommented* by some
# JS code, see query of class '.js-scroll-hidden' in Anna's HTML template:
# The rendering of the WEB page is very strange; except the first position
# all other positions of Anna's result page are enclosed in SGML comments.
# These comments are *uncommented* by some JS code, see query of class
# '.js-scroll-hidden' in Anna's HTML template:
# https://annas-software.org/AnnaArchivist/annas-archive/-/blob/main/allthethings/templates/macros/md5_list.html # https://annas-software.org/AnnaArchivist/annas-archive/-/blob/main/allthethings/templates/macros/md5_list.html
for item in eval_xpath_list(dom, '//main//div[contains(@class, "js-scroll-hidden")]'): for item in eval_xpath_list(dom, '//main//div[contains(@class, "js-aarecord-list-outer")]/div'):
item = html.fromstring(item.xpath('./comment()')[0].text) try:
results.append(_get_result(item)) results.append(_get_result(item))
except SearxEngineXPathException:
pass
return results return results
def _get_result(item): def _get_result(item):
return { return {
'template': 'paper.html', 'template': 'paper.html',
'url': base_url + extract_text(eval_xpath_getindex(item, './@href', 0)), 'url': base_url + extract_text(eval_xpath_getindex(item, './a/@href', 0)),
'title': extract_text(eval_xpath(item, './/h3/text()[1]')), 'title': extract_text(eval_xpath(item, './div//a[starts-with(@href, "/md5")]')),
'publisher': extract_text(eval_xpath(item, './/div[contains(@class, "text-sm")]')), 'authors': [extract_text(eval_xpath_getindex(item, './/a[starts-with(@href, "/search")]', 0))],
'authors': [extract_text(eval_xpath(item, './/div[contains(@class, "italic")]'))], 'publisher': extract_text(
'content': extract_text(eval_xpath(item, './/div[contains(@class, "text-xs")]')), eval_xpath_getindex(item, './/a[starts-with(@href, "/search")]', 1, default=None), allow_none=True
),
'content': extract_text(eval_xpath(item, './/div[contains(@class, "relative")]')),
'thumbnail': extract_text(eval_xpath_getindex(item, './/img/@src', 0, default=None), allow_none=True), 'thumbnail': extract_text(eval_xpath_getindex(item, './/img/@src', 0, default=None), allow_none=True),
} }