Merge branch 'master' into Develop

cps/helper.py

@@ -418,8 +418,6 @@ def rename_author_path(first_author, old_author_dir, renamed_author, calibre_pat
     # Create new_author_dir from parameter or from database
     # Create new title_dir from database and add id
     new_authordir = get_valid_filename(first_author, chars=96)
-    # new_author = calibre_db.session.query(db.Authors).filter(db.Authors.name == renamed_author).first()
-    # old_author_dir = get_valid_filename(old_author_name, chars=96)
     new_author_rename_dir = get_valid_filename(renamed_author, chars=96)
     if gdrive:
         g_file = gd.getFileFromEbooksFolder(None, old_author_dir)
@@ -468,7 +466,6 @@ def update_dir_structure_file(book_id, calibre_path, original_filepath, new_auth
                                      db_filename,
                                      original_filepath,
                                      path)
-        # old_path = os.path.join(calibre_path, author_dir, new_title_dir).replace('\\', '/')
         new_path = os.path.join(calibre_path, new_author_dir, new_title_dir).replace('\\', '/')
         all_new_name = get_valid_filename(local_book.title, chars=42) + ' - ' \
                        + get_valid_filename(new_author, chars=42)
@@ -477,8 +474,6 @@ def update_dir_structure_file(book_id, calibre_path, original_filepath, new_auth
 
         if error:
             return error
-
-    # Rename all files from old names to new names
     return False
 
 
@@ -490,7 +485,7 @@ def upload_new_file_gdrive(book_id, first_author, title, title_dir, original_fil
                                title_dir + " (" + str(book_id) + ")")
     book.path = gdrive_path.replace("\\", "/")
     gd.uploadFileToEbooksFolder(os.path.join(gdrive_path, file_name).replace("\\", "/"), original_filepath)
-    return False # rename_files_on_change(first_author, renamed_author, local_book=book, gdrive=True)
+    return False
 
 
 def update_dir_structure_gdrive(book_id, first_author):
@@ -523,19 +518,21 @@ def update_dir_structure_gdrive(book_id, first_author):
         all_new_name = get_valid_filename(book.title, chars=42) + ' - ' \
                        + get_valid_filename(new_authordir, chars=42)
         rename_all_files_on_change(book, book.path, book.path, all_new_name, gdrive=True)  # todo: Move filenames on gdrive
-    # change location in database to new author/title path
-    # book.path = os.path.join(authordir, new_titledir).replace('\\', '/')
     return False
 
 
 def move_files_on_change(calibre_path, new_author_dir, new_titledir, localbook, db_filename, original_filepath, path):
     new_path = os.path.join(calibre_path, new_author_dir, new_titledir)
-    # new_name = get_valid_filename(localbook.title, chars=96) + ' - ' + new_author_dir
     try:
         if original_filepath:
             if not os.path.isdir(new_path):
                 os.makedirs(new_path)
-            shutil.move(original_filepath, os.path.join(new_path, db_filename))
+            try:
+                shutil.move(original_filepath, os.path.join(new_path, db_filename))
+            except OSError:
+                log.error("Rename title from {} to {} failed with error, trying to "
+                          "move without metadata".format(path, new_path))
+                shutil.move(original_filepath, os.path.join(new_path, db_filename), copy_function=shutil.copy)
             log.debug("Moving title: %s to %s", original_filepath, new_path)
         else:
             # Check new path is not valid path

cps/metadata_provider/amazon.py

@@ -38,14 +38,16 @@ class Amazon(Metadata):
     __name__ = "Amazon"
     __id__ = "amazon"
     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'}
     session = requests.Session()
     session.headers=headers
@@ -62,7 +64,7 @@ class Amazon(Metadata):
                     log.warning(ex)
                     return []
                 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:
                     return []
                 try:
@@ -106,7 +108,7 @@ class Amazon(Metadata):
                     except (AttributeError, ValueError):
                         match.rating = 0
                     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):
                         match.cover = ""
                     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
                           soup.findAll("div", attrs={"data-component-type": "s-search-result"})]
             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)))
         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

cps/search_metadata.py

@@ -33,7 +33,6 @@ from cps.services.Metadata import Metadata
 from . import constants, logger, ub, web_server
 from .usermanagement import user_login_required
 
-# current_milli_time = lambda: int(round(time() * 1000))
 
 meta = Blueprint("metadata", __name__)
 
@@ -130,7 +129,7 @@ def metadata_search():
     locale = get_locale()
     if query:
         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:
             meta = {
                 executor.submit(c.search, query, static_cover, locale): c
@@ -139,5 +138,4 @@ def metadata_search():
             }
             for future in concurrent.futures.as_completed(meta):
                 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")