mirrors/calibre-web
1
0
Fork 0
mirror of https://github.com/janeczku/calibre-web synced 2024-09-21 03:39:46 +00:00
Code Issues Releases Wiki Activity

Fix metadata search results

Browse Source
This commit is contained in:
Ozzie Isaacs 2024-08-12 18:29:31 +02:00
parent 3733fd442f
commit 095074f977
2 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
cps/metadata_provider/amazon.py
View File

@ -53,7 +53,6 @@ class Amazon(Metadata):
def search( def search(
self, query: str, generic_cover: str = "", locale: str = "en" self, query: str, generic_cover: str = "", locale: str = "en"
) -> Optional[List[MetaRecord]]: ) -> Optional[List[MetaRecord]]:
#timer=time()
def inner(link, index) -> [dict, int]: def inner(link, index) -> [dict, int]:
with self.session as session: with self.session as session:
try: try:
@ -61,11 +60,11 @@ class Amazon(Metadata):
r.raise_for_status() r.raise_for_status()
except Exception as ex: except Exception as ex:
log.warning(ex) log.warning(ex)
return None return []
long_soup = BS(r.text, "lxml") #~4sec :/ long_soup = BS(r.text, "lxml") #~4sec :/
soup2 = long_soup.find("div", attrs={"cel_widget_id": "dpx-books-ppd_csm_instrumentation_wrapper"}) soup2 = long_soup.find("div", attrs={"cel_widget_id": "dpx-books-ppd_csm_instrumentation_wrapper"})
if soup2 is None: if soup2 is None:
return None return []
try: try:
match = MetaRecord( match = MetaRecord(
title = "", title = "",
@ -88,7 +87,7 @@ class Amazon(Metadata):
soup2.find("div", attrs={"data-feature-name": "bookDescription"}).stripped_strings)\ soup2.find("div", attrs={"data-feature-name": "bookDescription"}).stripped_strings)\
.replace("\xa0"," ")[:-9].strip().strip("\n") .replace("\xa0"," ")[:-9].strip().strip("\n")
except (AttributeError, TypeError): except (AttributeError, TypeError):
return None # if there is no description it is not a book and therefore should be ignored return [] # if there is no description it is not a book and therefore should be ignored
try: try:
match.title = soup2.find("span", attrs={"id": "productTitle"}).text match.title = soup2.find("span", attrs={"id": "productTitle"}).text
except (AttributeError, TypeError): except (AttributeError, TypeError):
@ -113,7 +112,7 @@ class Amazon(Metadata):
return match, index return match, index
except Exception as e: except Exception as e:
log.error_or_exception(e) log.error_or_exception(e)
return None return []
val = list() val = list()
if self.active: if self.active:
@ -134,6 +133,6 @@ class Amazon(Metadata):
soup.findAll("div", attrs={"data-component-type": "s-search-result"})] soup.findAll("div", attrs={"data-component-type": "s-search-result"})]
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor: with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
fut = {executor.submit(inner, link, index) for index, link in enumerate(links_list[:5])} fut = {executor.submit(inner, link, index) for index, link in enumerate(links_list[:5])}
val = list(map(lambda x : x.result() ,concurrent.futures.as_completed(fut))) val = list(map(lambda x : x.result(), concurrent.futures.as_completed(fut)))
result = list(filter(lambda x: x, val)) result = list(filter(lambda x: x, val))
return [x[0] for x in sorted(result, key=itemgetter(1))] #sort by amazons listing order for best relevance return [x[0] for x in sorted(result, key=itemgetter(1))] #sort by amazons listing order for best relevance

2
cps/metadata_provider/google.py
View File

@ -54,7 +54,7 @@ class Google(Metadata):
results.raise_for_status() results.raise_for_status()
except Exception as e: except Exception as e:
log.warning(e) log.warning(e)
return None return []
for result in results.json().get("items", []): for result in results.json().get("items", []):
val.append( val.append(
self._parse_search_result( self._parse_search_result(