def expand(xsl_filepath: Path,
xml_filepath: Path,
doctype: Optional[str] = None):
"""expand a template file using the book's book.xml metadata"""
template = lxml.etree.XSLT(read(xsl_filepath))
result = template(book)
xml.save(xml_filepath, result, doctype)
def getAll(file_name):
xml = open(file_name, "r") # 打开文件
data = xml.read() # 读取文件
lable = re.search('<label>[0-9]+',data)
lable = lable.group(0)[7:] #获取标签名
data = data.replace("\n","")
data = data.replace("\t","") #删除格式
while "<" in data : # 删除标签
start = data.index("<")
end = data.index(">")
data = data[:start] + data[end+1:]
f = open('ans.robot','a')
f.write("验证第" + lable+"条参考文献all")
f.write("\n" + " Jats Text Should Be ")
f.write(".//ref-list/ref[" + lable + "]")
f.write(" " + data + "\n\n")
import xml
from pathlib import Path
from xml import read
BOOK = Path(sys.argv[1])
EPUB = Path(sys.argv[2])
CODE = Path(__file__).parent
OEBPS = EPUB / 'OEBPS'
DEFAULTS = [CODE / 'templates' / 'epub', CODE / 'templates' / 'common']
TEMPLATES = CODE / 'templates' / 'epub' / 'XML'
book_dtd = lxml.etree.DTD(str(CODE / 'book.dtd'))
book = xml.read(BOOK / 'book.xml', dtd=book_dtd)
book.attrib['date'] = time.strftime("%Y-%m-%d")
def expand(xsl_filepath: Path,
xml_filepath: Path,
doctype: Optional[str] = None):
"""expand a template file using the book's book.xml metadata"""
template = lxml.etree.XSLT(read(xsl_filepath))
result = template(book)
xml.save(xml_filepath, result, doctype)
def copy_files(subdirectory: str, filenames: List[str]) -> None:
"""
copy files from BOOK to EPUB, using a default or template
def run(ebook: Path, bigbook: Path, ubercoordinator: Path,
files: List[Path]) -> None:
"""
:param ebook: the ebook source directory
:param bigbook: the Big Book of Key
:param ubercoordinator: the ubercoordinator source directory, for the DTD
:param files: the XHTML file from the Big Book of Key that need adding
:return:
"""
index = Index(bigbook)
book_dtd = DTD((ubercoordinator / 'src' / 'book.dtd').open())
book = xml.read(ebook / 'book.xml', dtd=book_dtd)
illustrations = xml.get_one(book, 'illustrations')
contents = xml.get_one(book, 'contents')
sections = set(
xml.get_all_str(contents, '//section[not(@template="yes")]/@file'))
images = set(xml.get_all_str(illustrations, '//image/@file'))
initial_sections = sections.copy()
initial_images = images.copy()
for filename in sections:
ebook_file = ebook / 'Text' / filename
bigbook_file = bigbook / 'Text' / filename
if not ebook_file.exists() and bigbook_file.exists():
copyfile(bigbook_file, ebook_file)
if ebook_file.exists():
for img_filename in find_images(ebook_file):
if img_filename not in images:
illustrations.append(file_element('image', img_filename))
images.add(img_filename)
else:
print(
f"{ebook / 'book.xml'}:0:0:WARNING: is this missing?: {filename}"
)
for file in files:
article_id = file.stem
article = index.articles_by_id[article_id]
if article.file.name not in sections:
copyfile(article.file, ebook / 'Text' / article.file.name)
title = xml.rewrap('title', XML(article.link))
section = file_element('section', article.file.name)
section.append(title)
contents.append(section)
sections.add(file.name)
for img_filename in find_images(article.file):
if img_filename not in images:
illustrations.append(file_element('image', img_filename))
images.add(img_filename)
for img_filename in images:
file = ebook / 'Images' / img_filename
if not file.exists():
copyfile(bigbook / 'Images' / img_filename, file)
book.attrib['date'] = strftime("%Y-%m-%d")
if sections != initial_sections or images != initial_images:
copyfile(ebook / 'book.xml', ebook / 'book.xml.bak')
xml.save(ebook / 'book.xml', book, doctype='book')
def search(startRecord, maxRecords, *args):
"""This function passes your queries, separated by commas, in addition to the record you'd like to start with. """
oErr = ErrHandle()
RECHERCHE_BASEURL = "https://gallica.bnf.fr/SRU"
try:
for arg in args:
search_string = (', '.join('"' + item + '"' for item in arg))
oData = {}
oData['operation'] = 'searchRetrieve'
oData['version'] = "1.2"
# oData['query'] = "((dc.language any lat) and (gallica all {}))".format(search_string)
oData['query'] = urllib.parse.quote("((dc.language any \"lat\" \"latin\") and (dc.type any \"manuscript\" \"manuscrit\") and (dc.title any {}))".format(search_string))
oData['query'] = "((dc.language all \"lat\") and (dc.type all \"manuscrit\") and (notice any {}))".format(search_string)
oData['query'] = "( (dc.language all \"lat\") and (dc.title adj \"latin\"))"
oData['query'] = "( (dc.language all \"lat\") and (dc.source adj \"département des manuscrits\"))"
oData['maximumRecords'] = maxRecords
oData['startRecord'] = startRecord
# Combine the data into an URL
sData = ""
for k,v in oData.items():
if sData == "":
sData = "?"
else:
sData = sData + "&"
sData = sData + k + "=" + v
url = RECHERCHE_BASEURL + sData
print(url)
attempts = 10
bSuccess = False
root = None
except:
oErr.DoError("Search/search error 1")
return ""
# set up a filename
filename = "gallica_{}.xml".format(startRecord)
while not bSuccess and attempts > 0:
# Show progess if attempts are lower than 10
if attempts < 10:
print("Attempts left: {}".format(attempts))
bHaveRequest = True
try:
r = requests.get(url)
except:
oErr.DoError("Search/search error 2")
bHaveRequest = False
# Action depends on what we receive
if bHaveRequest and r.status_code == 200:
# Read the content
contents = r.text
# contents = s.read()
try:
# Write the contents to a local directory Gallica.xml
file = open(filename, 'w', encoding="utf-8-sig")
file.write(contents)
file.close()
# Open this file and parse it as xml
with open(filename, encoding="utf-8-sig") as xml:
# Read the text
sText = xml.read()
# Convert text to XML object
root = ET.fromstring(sText)
# Indicate we have it
bSuccess = True
except:
oErr.DoError("Could not read the XML")
return ""
else:
oErr.Status("Site returns status: {}".format(r.status_code))
# Keep track of attempts
attempts -= 1
if bSuccess:
# return this document
return root
else:
# Were not able to process the request
oErr.DoError("Could not process the request")
return ""