research/resources
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify scripts

Browse Source
This commit is contained in:
oscarz
2025-03-18 18:01:49 +08:00
parent d28acc0556
commit 96ab26c429
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
aabook/src/scraper.py
View File

@ -189,7 +189,7 @@ def pase_chapter_list(soup, url):
chap_data = [] chap_data = []
for chap in chap_list: for chap in chap_list:
chap_title = chap.get_text().strip() chap_title = chap.get_text().strip()
chap_link = f'{host_url}/{chap['href']}' chap_link = f"{host_url}/{chap['href']}"
chap_id = utils.extract_page_num(chap_link) chap_id = utils.extract_page_num(chap_link)
chap_data.append({'href': chap_link, 'title': chap_title, 'chapter_id': chap_id}) chap_data.append({'href': chap_link, 'title': chap_title, 'chapter_id': chap_id})
table_of_contents.append({'title': section_title, 'chapters': chap_data}) table_of_contents.append({'title': section_title, 'chapters': chap_data})
@ -250,7 +250,7 @@ def parse_chapter_page(soup, url):
if next_div: if next_div:
next_page_tag = next_div.find('a', href=True, title=re.compile(r'下一章')) next_page_tag = next_div.find('a', href=True, title=re.compile(r'下一章'))
if next_page_tag: if next_page_tag:
next_url = f'{host_url}/{next_page_tag['href']}' if next_page_tag['href'] else '' next_url = f"{host_url}/{next_page_tag['href']}" if next_page_tag['href'] else ''
data = {'title': title, 'content_url': content_url, 'table_of_contents': table_of_contents} data = {'title': title, 'content_url': content_url, 'table_of_contents': table_of_contents}
return data, next_url return data, next_url