PHB/BibAPI
2
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases 4 Wiki Activity

dev #10

Merged
WorldTeacher merged 3 commits from dev into main 2025-11-25 09:13:05 +00:00
Conversation 0 Commits 3 Files Changed 3 +34 -32
1 changed files with 34 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 97a1becc86 - Show all commits

66
src/bibapi/catalogue.py
View File

@@ -44,7 +44,6 @@ class Catalogue:
def get_book(self, searchterm: str):
links = self.get_book_links(searchterm)
print(links)
for elink in links:
result = self.search(elink)
# in result search for class col-xs-12 rds-dl RDS_LOCATION
@@ -56,12 +55,14 @@ class Catalogue:
title = title_el.get_text(strip=True) if title_el else None
ppn_el = soup.find(
"div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PPN"
"div",
class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PPN",
)
# in ppn_el, get text of div col-xs-12 col-md-7 col-lg-8 rds-dl-panel
ppn = (
ppn_el.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
).get_text(strip=True)
if ppn_el
else None
@@ -69,18 +70,21 @@ class Catalogue:
# get edition text at div class col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_EDITION
edition_el = soup.find(
"div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_EDITION"
"div",
class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_EDITION",
)
edition = (
edition_el.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
).get_text(strip=True)
if edition_el
else None
)
authors = soup.find_all(
"div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PERSON"
"div",
class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PERSON",
)
author = None
if authors:
@@ -88,7 +92,8 @@ class Catalogue:
author_names = []
for author in authors:
panel = author.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
)
if panel:
links = panel.find_all("a")
@@ -105,7 +110,7 @@ class Catalogue:
groups = []
cur = {}
for node in panel.select(
"div.rds-dl.RDS_SIGNATURE, div.rds-dl.RDS_STATUS, div.rds-dl.RDS_LOCATION, div.col-xs-12.space"
"div.rds-dl.RDS_SIGNATURE, div.rds-dl.RDS_STATUS, div.rds-dl.RDS_LOCATION, div.col-xs-12.space",
):
classes = node.get("class", [])
# Separator between entries
@@ -147,16 +152,15 @@ class Catalogue:
author=author,
edition=edition,
)
else:
return Book(
title=title,
ppn=ppn,
signature=signature,
library_location=loc.split("\n\n")[-1],
link=elink,
author=author,
edition=edition,
)
return Book(
title=title,
ppn=ppn,
signature=signature,
library_location=loc.split("\n\n")[-1],
link=elink,
author=author,
edition=edition,
)
def get_book_with_data(self, searchterm: str) -> Book | None:
book = self.get_book(searchterm)
@@ -168,19 +172,18 @@ class Catalogue:
# from div col-xs-12 rds-dl RDS_SIGNATURE get signature (second div in this div)
signature = None
signature_el = soup.find("div", class_="RDS_SIGNATURE")
print(signature_el)
if signature_el:
signature = signature_el.find("div", class_="rds-dl-panel").get_text(
strip=True
strip=True,
)
print(signature)
book.signature = signature
# from div col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_ISBN get isbn (second div in this div)
isbn = None
isbn_el = soup.find("div", class_="RDS_ISBN")
if isbn_el:
isbn = isbn_el.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
).get_text(strip=True)
book.isbn = isbn
# from div col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_SCOPE get pages (second div in this div)
@@ -188,7 +191,8 @@ class Catalogue:
pages_el = soup.find("div", class_="RDS_SCOPE")
if pages_el:
pages = pages_el.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
).get_text(strip=True)
# regex match to get pages by grabbing the first number in the string
match = regex.search(r"(\d+)", pages)
@@ -210,7 +214,6 @@ class Catalogue:
for link in links:
result = self.search(link)
soup = BeautifulSoup(result, "html.parser")
print(link)
ppn = link.split("/")[-1]
if ppn and regex.match(r"^\d{8,10}[X\d]?$", ppn):
return ppn
@@ -239,19 +242,20 @@ class Catalogue:
links = self.get_book_links(f"kid:{link}")
author = None
for link in links:
# print(link)
result = self.search(link)
soup = BeautifulSoup(result, "html.parser")
# get all authors, return them as a string seperated by ;
authors = soup.find_all(
"div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PERSON"
"div",
class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PERSON",
)
if authors:
# get the names of the a href links in the div col-xs-12 col-md-7 col-lg-8 rds-dl-panel
author_names = []
for author in authors:
panel = author.find_next_sibling(
"div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
"div",
class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel",
)
if panel:
links = panel.find_all("a")
@@ -272,7 +276,7 @@ class Catalogue:
groups = []
cur = {}
for node in panel.select(
"div.rds-dl.RDS_SIGNATURE, div.rds-dl.RDS_STATUS, div.rds-dl.RDS_LOCATION, div.col-xs-12.space"
"div.rds-dl.RDS_SIGNATURE, div.rds-dl.RDS_STATUS, div.rds-dl.RDS_LOCATION, div.col-xs-12.space",
):
classes = node.get("class", [])
# Separator between entries
@@ -302,14 +306,12 @@ class Catalogue:
# Find the signature for the entry whose location mentions "Semesterapparat"
for g in groups:
print(g)
loc = g.get("location", "").lower()
if "semesterapparat" in loc:
signature = g.get("signature")
return signature
else:
signature = g.get("signature")
return signature
signature = g.get("signature")
return signature
print("No signature found")
return signature