def get_text(text_id, base_dir):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"mahaabhaarata/kumbhakonam.json")
if text_id == "BORI":
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"mahaabhaarata/bori.json")
else:
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"mahaabhaarata/kumbhakonam.json")
for book_index in text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[]):
book_index = "%02d" % book_index
chapter_list = text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[book_index])
book_data = text_data.get_subunit_data(json_file=unit_info_file,
unit_path_list=[book_index])
for chapter_index in chapter_list:
infile_path = "http://mahabharata.manipal.edu/browse/%s/%s/%d.txt" % (
book_data["alt_title"].lower(), text_id, chapter_index)
outfile_path = os.path.join(base_dir, str(book_index),
"%03d.md" % chapter_index)
logging.info("Book %s chapter %d url: %s outpath: %s", book_index,
chapter_index, infile_path, outfile_path)
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
with open(outfile_path, "w") as outfile:
resource = urllib.request.urlopen(infile_path)
content = resource.read().decode("utf-8")
outfile.writelines([content])
def dump_text(base_dir, do_transliteration=False):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "shatapatha.json")
titus_url = "http://titus.uni-frankfurt.de/texte/etcs/ind/aind/ved/yvw/sbm/sbm.htm"
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[]):
sarga_list = text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[kaanda_index])
for sarga_index in sarga_list:
logging.info("kaanDa %d adhyaaya %d", kaanda_index, sarga_index)
outfile_path = os.path.join(base_dir, "%02d" % (kaanda_index), "%02d" % sarga_index + ".md")
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
titus.navigate_to_part(base_page_url=titus_url, level_3_id=kaanda_index, level_4_id=sarga_index)
sentences = titus.get_text()
lines = ["\n"]
for sentence in sentences:
sentence = roman.RomanScheme.simplify_accent_notation(sentence)
sentence = sentence.replace("/", ".")
if not sentence.endswith("."):
sentence = sentence + ".."
if do_transliteration:
if kaanda_index == 12:
sentence = sanscript.transliterate(sentence, sanscript.IAST, sanscript.DEVANAGARI)
else:
sentence = sanscript.transliterate(sentence, sanscript.TITUS, sanscript.DEVANAGARI)
sentence = roman.RomanScheme.to_shatapatha_svara(sentence)
lines.append(sentence + " \n")
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
with open(outfile_path, "w") as outfile:
outfile.writelines(lines)
def dump_text(base_dir):
opts = options.Options()
opts.headless = False
browser = webdriver.Chrome(options=opts)
browser.implicitly_wait(6)
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "vedaH/shaunaka/samhitA.json")
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[]):
subunit_list = text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[kaanda_index])
for subunit_index in subunit_list:
logging.info("kaanDa %d adhyaaya %d", kaanda_index, subunit_index)
outfile_path = os.path.join(base_dir, "%02d" % (kaanda_index), "%03d.md" % subunit_index)
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
url = "http://vedicheritage.gov.in/samhitas/atharvaveda-samhitas/shaunaka-samhita/kanda-%02d-sukta-%03d/" % (
kaanda_index, subunit_index)
logging.info("url %s to %s", url, outfile_path)
browser.get(url=url)
text = browser.find_element_by_id("videotext").text
text = text.replace("\n", " \n")
title_tags = browser.find_elements_by_css_selector("#videotext strong")
title = "%03d" % subunit_index
if len(title_tags) > 0:
title = "%03d %s" % (subunit_index, title_tags[0].text)
title = sanscript.transliterate(title, sanscript.HK, sanscript.DEVANAGARI)
md_file = MdFile(file_path=outfile_path)
md_file.dump_to_file(metadata={"title": title}, content=text, dry_run=False)
browser.close()
def test_get_subunit_list():
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"shatapatha.json")
assert text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[]) == range(1, 15)
assert text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[2]) == range(1, 7)
def dump_text(base_dir):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"veda/shaunaka/samhitA.json")
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[]):
subunit_list = text_data.get_subunit_list(
json_file=unit_info_file, unit_path_list=[kaanda_index])
for subunit_index in subunit_list:
logging.info("kaanDa %d adhyaaya %d", kaanda_index, subunit_index)
outfile_path = os.path.join(base_dir, "%02d" % (kaanda_index),
"%03d.md" % subunit_index)
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
url = "http://vedicheritage.gov.in/samhitas/atharvaveda-samhitas/shaunaka-samhita/kanda-%02d-sukta-%03d/" % (
kaanda_index, subunit_index)
logging.info("url %s to %s", url, outfile_path)
browser.get(url=url)
text = browser.find_element_by_id("videotext").text
text = text.replace("\n", " \n")
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
with open(outfile_path, "w") as outfile:
logging.debug(text)
outfile.write(text)
def get_text(text_id, base_dir):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "mahaabhaaratam/kumbhakonam.json")
if text_id == "BORI":
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "mahaabhaaratam/bori.json")
elif text_id == "KK":
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "mahaabhaaratam/kumbhakonam.json")
elif text_id == "SV":
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "mahaabhaaratam/vAvilla.json")
for book_index in text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[]):
book_index = "%02d" % book_index
chapter_list = text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[book_index])
for chapter_index in chapter_list:
infile_path = "http://mahabharata.manipal.edu/anu-projects/MAHE/apiphpv5/readMaha2.php?src=%s&parva=%s&adh=%03d" % (text_id, book_index, chapter_index)
outfile_path = os.path.join(base_dir, str(book_index), "%03d.md" % chapter_index)
if os.path.exists(outfile_path):
logging.warning("Skipping " + outfile_path)
continue
logging.info("Book %s chapter %d url: %s outpath: %s", book_index, chapter_index, infile_path, outfile_path)
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
resource = urllib.request.urlopen(infile_path)
content = resource.read().decode("utf-8")
chapter_lines = [line["text"] + " \n" for line in json.loads(content)]
if len(chapter_lines) > 0:
with open(outfile_path, "w") as outfile:
outfile.writelines(chapter_lines)
else:
logging.error("No lines found for %s:%s-%03d", text_id, book_index, chapter_index)
def dump_text(base_dir):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"vedaH/vAjasaneyi/samhitA.json")
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[]):
logging.info("adhyAya %d", kaanda_index)
outfile_path = os.path.join(base_dir, "%02d.md" % (kaanda_index))
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
url = "http://vedicheritage.gov.in/samhitas/yajurveda/shukla-yajurveda/vajasaneyi-kanva-samhita-chapter-%02d/" % (
kaanda_index)
logging.info("url %s to %s", url, outfile_path)
browser.get(url=url)
try:
text = browser.find_element_by_id("videotext").text
text = text.replace("\n", " \n")
title = "%02d" % kaanda_index
title = sanscript.transliterate(title, sanscript.HK,
sanscript.DEVANAGARI)
md_file = MdFile(file_path=outfile_path)
md_file.dump_to_file(metadata={"title": title},
md=text,
dry_run=False)
except NoSuchElementException:
logging.warning("Page missing! %s ", url)
def get_ramayana_text(browser, text_id, base_dir):
browser.find_element_by_link_text(text_id).click()
# browser.implicitly_wait(2)
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"raamaayana/andhra.json")
if text_id == "रामायणम्-नव्यपाठः":
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"raamaayana/baroda.json")
else:
unit_info_file = os.path.join(os.path.dirname(text_data.__file__),
"raamaayana/kumbhakonam.json")
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[]):
kaanda_element = browser.find_element_by_link_text("Kanda-%d" %
kaanda_index)
# kaanda_element.click()
# Sometimes headless browser fails with selenium.common.exceptions.ElementClickInterceptedException: Message: element click intercepted . Then, non-headless browser works fine! Or can try https://stackoverflow.com/questions/48665001/can-not-click-on-a-element-elementclickinterceptedexception-in-splinter-selen
browser.execute_script("arguments[0].click();", kaanda_element)
sarga_list = text_data.get_subunit_list(json_file=unit_info_file,
unit_path_list=[kaanda_index])
for sarga_index in sarga_list:
logging.info("Kanda %d Sarga %d", kaanda_index, sarga_index)
outfile_path = os.path.join(base_dir, str(kaanda_index),
"%03d" % sarga_index + ".md")
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
browser.find_element_by_link_text("Sarga-%d" % sarga_index).click()
text_spans = browser.find_element_by_id(
"divResults").find_elements_by_tag_name("span")
lines = ["\n", "\n"]
for span in text_spans:
shloka = span.text
shloka = shloka.replace("। ", "। \n")
shloka = shloka.replace("।।", " ॥ ")
lines.append(shloka + " \n")
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
with open(outfile_path, "w") as outfile:
outfile.writelines(lines)
# Close the kANDa - else the driver may pick sarga from this kANDa when it is to pick the sarga from the next kANDa?!
browser.find_element_by_link_text("Kanda-%d" % kaanda_index).click()
def dump_text(base_dir, do_transliteration=False):
unit_info_file = os.path.join(os.path.dirname(text_data.__file__), "vedaH/vAjasaneyi/samhitA.json")
titus_url = "http://titus.uni-frankfurt.de/texte/etcd/ind/aind/ved/yvw/vs/vs.htm"
for kaanda_index in text_data.get_subunit_list(json_file=unit_info_file, unit_path_list=[]):
logging.info("kaanDa %d", kaanda_index)
outfile_path = os.path.join(base_dir, "%02d.md" % (kaanda_index))
if os.path.exists(outfile_path):
logging.info("Skipping " + outfile_path)
continue
titus.navigate_to_part(base_page_url=titus_url, level_3_id=kaanda_index, level_3_frame="etaindexb")
sentences = titus.dump_text()
os.makedirs(name=os.path.dirname(outfile_path), exist_ok=True)
with open(outfile_path, "w") as outfile:
outfile.write(" \n".join(sentences))
