lxbfYeaa/BookConverter
Archived
Template
1
0
Fork 0
forked from LiveCarta/BookConverter
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add anchor link to start page

Browse Source
This commit is contained in:
Svitin Egor
2025-03-25 12:56:57 +03:00
parent be6e85ec11
commit b765f66d41
1 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/epub_converter/epub_converter.py
View File

@@ -284,6 +284,14 @@ class EpubConverter:
self.adjacency_list[-1].append(nav_point) self.adjacency_list[-1].append(nav_point)
self.hrefs_added_to_toc.add(file) self.hrefs_added_to_toc.add(file)
@staticmethod
def create_new_anchor_span_start_page(soup: BeautifulSoup, id_: str) -> Tag:
new_anchor_span = soup.new_tag("span")
new_anchor_span.attrs["id"] = id_
new_anchor_span.attrs["class"] = "link-anchor-start"
new_anchor_span.string = "\xa0"
return new_anchor_span
def label_subchapters_with_lc_tag(self): def label_subchapters_with_lc_tag(self):
for html_href, soup in self.html_href2html_body_soup.items(): for html_href, soup in self.html_href2html_body_soup.items():
for i in self.html_href2subchapters_ids[html_href]: for i in self.html_href2subchapters_ids[html_href]:
@@ -291,6 +299,12 @@ class EpubConverter:
# in order not to lose tags in verification of same level in chapter # in order not to lose tags in verification of same level in chapter
parent_tags = tag.find_parents(['body', 'p', 'span', 'h1', 'h2', 'h3', 'h4', 'h5']) parent_tags = tag.find_parents(['body', 'p', 'span', 'h1', 'h2', 'h3', 'h4', 'h5'])
parent_tag = parent_tags[-1] if parent_tags else tag parent_tag = parent_tags[-1] if parent_tags else tag
# insert link to page
new_unique_id = self.create_unique_id(html_href, '')
parent_tag.insert_after(self.create_new_anchor_span_start_page(soup, new_unique_id))
self.internal_anchors.add(new_unique_id)
tmp_tag = soup.new_tag("lc_tmp") tmp_tag = soup.new_tag("lc_tmp")
tmp_tag.attrs["class"] = "converter-chapter-mark" tmp_tag.attrs["class"] = "converter-chapter-mark"
tmp_tag.attrs["id"] = i tmp_tag.attrs["id"] = i
@@ -391,8 +405,11 @@ class EpubConverter:
for href_from_toc in self.hrefs_added_to_toc: for href_from_toc in self.hrefs_added_to_toc:
for tag in self.html_href2html_body_soup[href_from_toc].find_all(attrs={"id": re.compile(r".+")}): for tag in self.html_href2html_body_soup[href_from_toc].find_all(attrs={"id": re.compile(r".+")}):
if tag.attrs.get("class") not in ["converter-chapter-mark", "footnote-element"]: if tag.attrs.get("class") not in ["converter-chapter-mark", "footnote-element"]:
new_unique_id = self.create_unique_id( if tag.attrs.get("class") == 'link-anchor-start':
href_from_toc, tag.attrs["id"]) new_unique_id = tag.attrs["id"]
tag.attrs["class"] = 'link-anchor'
else:
new_unique_id = self.create_unique_id(href_from_toc, tag.attrs["id"])
tag.attrs["id"] = new_unique_id tag.attrs["id"] = new_unique_id
def process_file_anchor(): def process_file_anchor():