krispire/spsays-training
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: bg verses now show range of verses

Browse Source
This commit is contained in:
gosangam
2026-04-14 14:46:16 +05:30
parent 82b6685c97
commit 83fec22f53
37 changed files with 151 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/bg_extract.py
+24 -8
View File
@@ -212,7 +212,7 @@ def extract_verses(soup: BeautifulSoup, max_chapter=1, max_verse=5):
current_verse = None
state = "IDLE" # IDLE, TRANSLITERATION, SYNONYMS, TRANSLATION, PURPORT
current_chapter = 0
chapter_title = ""
chapter_titles = {}
for p in paragraphs:
cls = get_css_class(p)
@@ -224,7 +224,9 @@ def extract_verses(soup: BeautifulSoup, max_chapter=1, max_verse=5):
match = re.match(r"^(\d+)\.\s+(.+)$", decoded, re.DOTALL)
if match:
current_chapter = int(match.group(1))
chapter_title = match.group(2).replace("\n", " ").strip()
chapter_titles[current_chapter] = (
match.group(2).replace("\n", " ").strip()
)
if current_chapter > max_chapter:
break
@@ -245,11 +247,25 @@ def extract_verses(soup: BeautifulSoup, max_chapter=1, max_verse=5):
if ch > max_chapter or (ch == max_chapter and vs > max_verse):
break
raw_ref = decode_scagoudy(text.strip())
# For multi-verse entries like "Bg 1.16, Bg 1.17, Bg 1.18, Bg 1.16-18",
# use only the last part: "Bg 1.16-18"
if "," in raw_ref:
clean_ref = raw_ref.rsplit(",", 1)[-1].strip()
else:
clean_ref = raw_ref
# Detect verse range (e.g., "Bg 1.16-18")
verse_end = None
range_match = re.search(r"Bg\s+\d+\.(\d+)-(\d+)", clean_ref)
if range_match:
verse_end = int(range_match.group(2))
current_verse = {
"book_title": "Bhagavad-gītā As It Is",
"chapter": ch,
"verse": vs,
"reference": decode_scagoudy(text.strip()),
"reference": clean_ref,
"devanagari": "",
"transliteration": "",
"_padas": [], # raw pādas, paired into lines later
@@ -257,6 +273,8 @@ def extract_verses(soup: BeautifulSoup, max_chapter=1, max_verse=5):
"translation": "",
"purport": [],
}
if verse_end is not None:
current_verse["verse_end"] = verse_end
state = "VERSE_START"
# TEXT header (e.g., "TEXT 1")
@@ -323,7 +341,7 @@ def extract_verses(soup: BeautifulSoup, max_chapter=1, max_verse=5):
_finalize_verse(current_verse)
verses.append(current_verse)
return verses, current_chapter, chapter_title
return verses, chapter_titles
def write_json(data, filepath):
@@ -344,9 +362,7 @@ def main():
soup = BeautifulSoup(f, "html.parser")
print("Extracting verses (all 18 chapters)...")
verses, chapter_num, chapter_title = extract_verses(
soup, max_chapter=18, max_verse=999
)
verses, chapter_titles = extract_verses(soup, max_chapter=18, max_verse=999)
print(f"\nExtracted {len(verses)} verses")
@@ -365,7 +381,7 @@ def main():
"author": "His Divine Grace A.C. Bhaktivedanta Swami Prabhupāda",
"totalChapters": 18,
"chapters": [
{"number": ch, "totalVerses": count}
{"number": ch, "title": chapter_titles.get(ch, ""), "totalVerses": count}
for ch, count in sorted(chapters_info.items())
],
}