mirrors/calibre-web
1
0
Fork 0
mirror of https://github.com/janeczku/calibre-web synced 2024-11-14 05:44:53 +00:00
Code Issues Releases Wiki Activity

Fix for load metadata from amazon

Browse Source
This commit is contained in:
Ozzie Isaacs 2024-09-14 10:23:11 +02:00
parent 481237dc77
commit 88cb58c285
2 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
cps/metadata_provider/amazon.py
View File

@ -38,14 +38,16 @@ class Amazon(Metadata):
__name__ = "Amazon" __name__ = "Amazon"
__id__ = "amazon" __id__ = "amazon"
headers = {'upgrade-insecure-requests': '1', headers = {'upgrade-insecure-requests': '1',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36', 'user-agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:130.0) Gecko/20100101 Firefox/130.0',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9', 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/png,image/svg+xml,*/*;q=0.8',
'sec-gpc': '1', 'Sec-Fetch-Site': 'same-origin',
'sec-fetch-site': 'none', 'Sec-Fetch-Mode': 'navigate',
'sec-fetch-mode': 'navigate', 'Sec-Fetch-User': '?1',
'sec-fetch-user': '?1', 'Sec-Fetch-Dest': 'document',
'sec-fetch-dest': 'document', 'Upgrade-Insecure-Requests': '1',
'accept-encoding': 'gzip, deflate, br', 'Alt-Used' : 'www.amazon.com',
'Priority' : 'u=0, i',
'accept-encoding': 'gzip, deflate, br, zstd',
'accept-language': 'en-US,en;q=0.9'} 'accept-language': 'en-US,en;q=0.9'}
session = requests.Session() session = requests.Session()
session.headers=headers session.headers=headers
@ -62,7 +64,7 @@ class Amazon(Metadata):
log.warning(ex) log.warning(ex)
return [] 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-ppd_csm_instrumentation_wrapper"})
if soup2 is None: if soup2 is None:
return [] return []
try: try:
@ -106,7 +108,7 @@ class Amazon(Metadata):
except (AttributeError, ValueError): except (AttributeError, ValueError):
match.rating = 0 match.rating = 0
try: try:
match.cover = soup2.find("img", attrs={"class": "a-dynamic-image frontImage"})["src"] match.cover = soup2.find("img", attrs={"class": "a-dynamic-image"})["src"]
except (AttributeError, TypeError): except (AttributeError, TypeError):
match.cover = "" match.cover = ""
return match, index return match, index
@ -132,7 +134,7 @@ class Amazon(Metadata):
links_list = [next(filter(lambda i: "digital-text" in i["href"], x.findAll("a")))["href"] for x in links_list = [next(filter(lambda i: "digital-text" in i["href"], x.findAll("a")))["href"] for x in
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[:3])}
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

4
cps/search_metadata.py
View File

@ -33,7 +33,6 @@ from cps.services.Metadata import Metadata
from . import constants, logger, ub, web_server from . import constants, logger, ub, web_server
from .usermanagement import user_login_required from .usermanagement import user_login_required
# current_milli_time = lambda: int(round(time() * 1000))
meta = Blueprint("metadata", __name__) meta = Blueprint("metadata", __name__)
@ -130,7 +129,7 @@ def metadata_search():
locale = get_locale() locale = get_locale()
if query: if query:
static_cover = url_for("static", filename="generic_cover.jpg") static_cover = url_for("static", filename="generic_cover.jpg")
# start = current_milli_time() # ret = cl[0].search(query, static_cover, locale)
with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor: with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
meta = { meta = {
executor.submit(c.search, query, static_cover, locale): c executor.submit(c.search, query, static_cover, locale): c
@ -139,5 +138,4 @@ def metadata_search():
} }
for future in concurrent.futures.as_completed(meta): for future in concurrent.futures.as_completed(meta):
data.extend([asdict(x) for x in future.result() if x]) data.extend([asdict(x) for x in future.result() if x])
# log.info({'Time elapsed {}'.format(current_milli_time()-start)})
return Response(json.dumps(data), mimetype="application/json") return Response(json.dumps(data), mimetype="application/json")