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

Merge pull request 'dev' (#10) from dev into main

Browse Source 
Reviewed-on: #10
This commit was merged in pull request #10.
This commit is contained in:
WorldTeacher
2025-11-25 09:13:04 +00:00
parent c8b3590355 97a1becc86
commit 4eb3856c36
3 changed files with 51 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
pyproject.toml
View File

@@ -8,13 +8,26 @@ authors = [
]
requires-python = ">=3.13"
dependencies = [
"beautifulsoup4>=4.14.2",
"cloudscraper>=1.2.71",
"playwright>=1.55.0",
"regex>=2025.9.18",
]
[project.optional-dependencies]
# SRU API feature: for accessing library catalogs via SRU protocol
sru = [
"requests>=2.32.5",
]
# Catalogue feature: web scraping local library catalog
catalogue = [
"requests>=2.32.5",
"beautifulsoup4>=4.12.0",
]
# Install all features
all = [
"bibapi[sru,catalogue]",
]
[build-system]
requires = ["uv_build >= 0.9.5, <0.10.0"]
build-backend = "uv_build"

83
src/bibapi/__init__.py
View File

@@ -1,5 +1,4 @@
from enum import Enum
from .schemas.api_types import *
from .sru import Api as _Api
__all__ = [
@@ -12,86 +11,6 @@ __all__ = [
]
class PicaSchema(Enum):
TITLE = "pica.tit"
CALLSIGN = "pica.abr"
ALL = "pica.all"
DATE_FIRST_CREATION = "pica.ser"
DATE_LAST_MODIFIED = "pica.aed"
ISBN = "pica.isb"
ISSN = "pica.isn"
ISMN = "pica.ism"
PPN = "pica.ppn"
AUTHOR = "pica.per"
YEAR = "pica.jhr"
AUTHOR_SCHEMA = "NoSpaceAfterComma"
ENCLOSE_TITLE_IN_QUOTES = False
class ALMASchema(Enum):
TITLE = "alma.title"
AUTHOR = "alma.author"
ENCLOSE_TITLE_IN_QUOTES = True
AUTHOR_SCHEMA = "NoSpaceAfterComma"
YEAR = "date_of_publication"
class DublinCoreSchema(Enum):
TITLE = "dc.title"
AUTHOR = "dc.creator"
AUTHOR_SCHEMA = "SpaceAfterComma"
ENCLOSE_TITLE_IN_QUOTES = False
YEAR = "dc.date"
class CQLSchema(Enum):
pass
class SWBSchema(Enum):
URL = "https://sru.k10plus.de/opac-de-627!rec=1?version=1.1&operation=searchRetrieve&query={}&maximumRecords=100&recordSchema=marcxml"
ARGSCHEMA = PicaSchema
NAME = "SWB"
LIBRARY_NAME_LOCATION_FIELD = "924$b"
class DNBSchema(Enum):
URL = "https://services.dnb.de/sru/dnb?version=1.1&operation=searchRetrieve&query={}&maximumRecords=100&recordSchema=MARC21-xml"
ARGSCHEMA = DublinCoreSchema
NAME = "DNB"
class KOBVSchema(Enum):
URL = "https://sru.kobv.de/k2?version=1.1&operation=searchRetrieve&query={}&startRecord=1&maximumRecords=100&recordSchema=marcxml"
ARGSCHEMA = DublinCoreSchema
NAME = "KOBV"
LIBRARY_NAME_LOCATION_FIELD = "924$b"
class HebisSchema(Enum):
URL = "http://sru.hebis.de/sru/DB=2.1?query={}&version=1.1&operation=searchRetrieve&stylesheet=http%3A%2F%2Fsru.hebis.de%2Fsru%2F%3Fxsl%3DsearchRetrieveResponse&recordSchema=marc21&maximumRecords=100&startRecord=1&recordPacking=xml&sortKeys=LST_Y%2Cpica%2C0%2C%2C"
ARGSCHEMA = PicaSchema
NOTSUPPORTEDARGS = ["YEAR"]
NAME = "HEBIS"
REPLACE = {" ": "+", "&": "%26", "=": "+%3D+"}
LIBRARY_NAME_LOCATION_FIELD = "924$b"
class OEVKSchema(Enum):
URL = "https://sru.k10plus.de/opac-de-627-2?version=1.1&operation=searchRetrieve&query={}&maximumRecords=100&recordSchema=marcxml"
ARGSCHEMA = PicaSchema
NAME = "OEVK"
LIBRARY_NAME_LOCATION_FIELD = "924$b"
class HBZSchema(Enum):
URL = "https://eu04.alma.exlibrisgroup.com/view/sru/49HBZ_NETWORK?version=1.2&operation=searchRetrieve&recordSchema=marcxml&query={}&maximumRecords=100&recordSchema=marcxml"
ARGSCHEMA = ALMASchema
NAME = "HBZ"
LIBRARY_NAME_LOCATION_FIELD = "852$a"
NOTSUPPORTEDARGS = ["PPN"]
class SWB(_Api):
def __init__(self):
self.site = SWBSchema.NAME.value

44
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
@@ -147,7 +152,6 @@ class Catalogue:
author=author,
edition=edition,
)
else:
return Book(
title=title,
ppn=ppn,
@@ -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
@@ -302,12 +306,10 @@ 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
print("No signature found")