def run_compare():
Helper.mkdir_p("results")
open("results/length_comparison.txt", "wb+").close() # just create it for now.
wlc_index_xml = ET.parse("source/TanachIndex.xml") # this lists num of chapters and verses for all books in the WLC
books_xml_r = wlc_index_xml.getroot().find("tanach")
for book in books_xml_r.findall("book"):
do_book_comparison(book)
def save_parsed_text(text, record="shmuel", part=""):
if record == "shmuel":
b = u"Tiferet Shmuel on " + masechet
a = u"Tiferet_Shmuel_on"
elif record == "yomtov":
b = u"Maadaney Yom Tov on " + masechet
a = u"Maadaney_Yom_Tov_on"
elif record == "chamudot":
a = u"Divrey_Chamudot_on"
b = u"Divrey Chamudot on " + masechet
text_whole = {
"title": b,
"versionTitle": "Vilna Edition",
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
#save
Helper.mkdir_p("../preprocess_json/")
if part == "":
with open("../preprocess_json/" + a + "_%s.json" % masechet,
'w') as out:
json.dump(text_whole, out)
else:
with open(
"../preprocess_json/" + a +
"_{}_{}.json".format(masechet, part), 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text, commentator):
print commentator
if "Korban Netanel" in commentator:
a = u" קרבן נתנאל על " + masechet_he
b = u"Korban Netanel on " + masechet
if "Pilpula Charifta" in commentator:
b = u"Pilpula Charifta on " + masechet
a = u" פילפולא חריפתא על " + masechet_he
text_whole = {
"title": b + masechet,
"versionTitle": "Vilna Edition",
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
#save
Helper.mkdir_p("../preprocess_json/")
saved_commetator = re.sub(" ", "_", commentator.strip())
with open("../preprocess_json/" + saved_commetator + "_%s.json" % masechet,
'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text, record = "shmuel" ):
if record == "shmuel":
b = u"Tiferet Shmuel on " + masechet
a = u"Tiferet_Shmuel_on"
elif record == "yomtov":
b= u"Maadaney Yom Tov on " + masechet
a = u"Maadaney_Yom_Tov_on"
elif record == "chamudot":
a = u"Divrey_Chamudot_on"
b = u"Divrey Chamudot on " + masechet
text_whole = {
"title": b,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/" + a + "_%s.json" % masechet , 'w') as out:
json.dump(text_whole, out)
def run_compare():
Helper.mkdir_p('results')
open("results/length_comparison.txt",
'wb+').close() #just create it for now.
wlc_index_xml = ET.parse(
'source/TanachIndex.xml'
) #this lists num of chapters and verses for all books in the WLC
books_xml_r = wlc_index_xml.getroot().find('tanach')
for book in books_xml_r.findall('book'):
do_book_comparison(book)
def save_parsed_text(text):
text_whole = {
"title": 'Chidushei Agadot on %s' %masechet,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Chidushei_Agadot_%s.json" % masechet, 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
text_whole = {
"title": 'Chidushei Agadot on %s' %masechet,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Chidushei_Agadot_%s.json" % masechet, 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
text_whole = {
"title": 'Rosh on Taanit',
"versionTitle": "Vilna, 1842",
"versionSource": "???",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rosh_on_Taanit.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
text_whole = {
"title": 'Rosh on Taanit',
"versionTitle": "Vilna, 1842",
"versionSource": "???",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rosh_on_Taanit.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Noda Byehuda',
"versionTitle": " ",
"versionSource": " ",
"language": "he",
"text": text,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Noda_Byehuda.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Teshuvot harambam',
"versionTitle": "Leipzig : H.L. Shnuis, 1859",
"versionSource": "http://www.worldcat.org/oclc/233123481",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/teshuvot_haRambam.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Meshech Hochma',
"versionTitle": "Srikot",
"versionSource": "",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Meshech Hochma.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Rashi on Genesis',
"versionTitle": "Pentateuch with Rashi's commentary by M. Rosenbaum and A.M. Silbermann",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001969084",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rashi_on_Genesis.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": "Haamek Davar on Exodus",
"versionTitle": "Vilna : 1879",
"versionSource": "http://babel.hathitrust.org/cgi/pt?id=uc1.31158011185906",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Haamek_Davar_on_Exodus.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Radak on Genesis',
"versionTitle": "Presburg : A. Schmid, 1842",
"versionSource": "http://www.worldcat.org/title/perush-radak-al-ha-torah-sefer-bereshit/oclc/867743220",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Radak on Genesis.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(book_name, text):
print "hello"
text_whole = {
"title": book_name,
"versionTitle": "On Your Way",
"versionSource": "http://mobile.tora.ws/",
"language": "he",
"text": text,
}
# save
Helper.mkdir_p("preprocess_json/Ben Ish Chai")
with open("preprocess_json/Ben Ish Chai/" + book_name + ".json", 'w') as out:
json.dump(text_whole, out)
post_to_api(book_name)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Mishnah'.format(masechet),
"versionTitle": "The Mishna with Obadiah Bartenura by Rabbi Shraga Silverstein",
"versionSource": "http://www.sefaria.org/shraga-silverstein",
"language": "en",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Shraga_Silverstein_translation_on_{}.json".format(masechet), 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'II Chronicles',
"versionTitle": "The Rashi chumash by Rabbi Shraga Silverstein",
"versionSource": "http://www.sefaria.org/shraga-silverstein",
"language": "en",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Shraga_Silverstein_translation_on_II_Chronicles.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": '%s' % commentator ,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/{}_on_{}.json".format(commentator,masechet), 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Meshech Hochma',
"versionTitle": "Srikot",
"versionSource": "",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Meshech Hochma.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(book_name, text):
print "hello"
text_whole = {
"title": book_name,
"versionTitle": "On Your Way",
"versionSource": "http://mobile.tora.ws/",
"language": "he",
"text": text,
}
# save
Helper.mkdir_p("preprocess_json/Ben Ish Chai")
with open("preprocess_json/Ben Ish Chai/" + book_name + ".json",
'w') as out:
json.dump(text_whole, out)
post_to_api(book_name)
def save_default_text(text):
text_whole = {
"title": 'Rosh on %s' % masechet,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rosh_on_{}.json".format(masechet), 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text, book):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Daat Zkenim on' + book,
"versionTitle": "Presburg : A. Schmid, 1842",
"versionSource":
"http://www.worldcat.org/title/perush-radak-al-ha-torah-sefer-bereshit/oclc/867743220",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Daat_Zkenim_on_" + book + ".json", 'w') as out:
json.dump(text_whole, out)
def save_default_text(text):
text_whole = {
"title": 'Rosh on %s' % masechet,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rosh_on_{}.json".format(masechet), 'w') as out:
json.dump(text_whole, out)
def save_file(intro):
text_whole = {
"title": "Haamek Davar Intro",
"versionTitle": "",
"versionSource": "",
"language": "he",
"text": intro,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Haamek_Davar_intro.json", 'w') as out:
json.dump(text_whole, out)
with open("preprocess_json/Haamek_Davar_intro.json", 'r') as filep:
file_text = filep.read()
createBookRecord(intro_basic_record())
Helper.postText("Haamek Davar Intro", file_text, False)
def save_parsed_text(parsed):
text_whole = {
"title": 'Prisha',
"versionTitle": "Vilna 1924",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001935970",
"language": "he",
"text": parsed,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Prisha.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Rashi on Genesis',
"versionTitle":
"Pentateuch with Rashi's commentary by M. Rosenbaum and A.M. Silbermann",
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001969084",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Rashi_on_Genesis.json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'II Chronicles',
"versionTitle": "The Rashi chumash by Rabbi Shraga Silverstein",
"versionSource": "http://www.sefaria.org/shraga-silverstein",
"language": "en",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open(
"preprocess_json/Shraga_Silverstein_translation_on_II_Chronicles.json",
'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": '%s' % commentator,
"versionTitle": "Wikisource " + commentator,
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/{}_on_{}.json".format(commentator, masechet),
'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Mishnah'.format(masechet),
"versionTitle":
"The Mishna with Obadiah Bartenura by Rabbi Shraga Silverstein",
"versionSource": "http://www.sefaria.org/shraga-silverstein",
"language": "en",
"text": text,
}
#save
Helper.mkdir_p("preprocess_json/")
with open(
"preprocess_json/Shraga_Silverstein_translation_on_{}.json".format(
masechet), 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(commentator, book_name, text):
#assemble the title ref
commentator_title = unicode(available_commentators[commentator]['record']['title'],'utf-8')
ref = commentator_title + ' on ' + book_name
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": ref,
"versionTitle": "On Your Way",
"versionSource": "http://mobile.tora.ws/",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p(preprocess_path + commentator + "/")
with open(preprocess_path + commentator + "/" + ref + ".json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(commentator, book_name, text):
#assemble the title ref
commentator_title = unicode(
available_commentators[commentator]['record']['title'], 'utf-8')
ref = commentator_title + ' on ' + book_name
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": ref,
"versionTitle": "On Your Way",
"versionSource": "http://mobile.tora.ws/",
"language": "he",
"text": text,
}
#save
Helper.mkdir_p(preprocess_path + commentator + "/")
with open(preprocess_path + commentator + "/" + ref + ".json", 'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text, chelek):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Terumat HaDeshen, ' + chelek,
"versionTitle": "Warsaw 1882",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001175907",
"language": "he",
"text": text,
"status":"locked",
"digitizedBySefaria" : True,
"licenseVetted" : True,
"license" : "Public Domain"
}
Helper.mkdir_p("preprocess_json/")
chelek = re.sub(" ", "_", chelek.strip())
with open("preprocess_json/Terumat_HaDeshen_{}.json".format(chelek), 'w') as out:
json.dump(text_whole, out)
def save_texts(main, additions, main_footnotes, added_footnotes):
main_text = {
"title": "Mekhilta DeRabbi Shimon Bar Yochai",
"versionTitle":
"Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource":
"https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": main,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi.json", 'w') as out:
json.dump(main_text, out)
text_additions = {
"title": "Mekhilta DeRabbi Shimon Bar Yochai Additions",
"versionTitle":
"Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource":
"https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": additions,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Added.json", 'w') as out:
json.dump(text_additions, out)
main_footnotes_text = {
"versionTitle":
"Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource":
"https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": main_footnotes,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Footnotes 1.json",
'w') as out:
json.dump(main_footnotes_text, out)
added_footnotes_text = {
"versionTitle":
"Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource":
"https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": added_footnotes,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Footnotes 2.json",
'w') as out:
json.dump(added_footnotes_text, out)
def save_parsed_text(text, chelek):
#print ref
#JSON obj matching the API requirements
text_whole = {
"title": 'Terumat HaDeshen, ' + chelek,
"versionTitle": "Warsaw 1882",
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001175907",
"language": "he",
"text": text,
"status": "locked",
"digitizedBySefaria": True,
"licenseVetted": True,
"license": "Public Domain"
}
Helper.mkdir_p("preprocess_json/")
chelek = re.sub(" ", "_", chelek.strip())
with open("preprocess_json/Terumat_HaDeshen_{}.json".format(chelek),
'w') as out:
json.dump(text_whole, out)
def save_parsed_text(text, commentator):
print commentator
if "Korban Netanel" in commentator:
a = u" קרבן נתנאל על " + masechet_he
b = u"Korban Netanel on " + masechet
if "Pilpula Charifta" in commentator:
b = u"Pilpula Charifta on " + masechet
a = u" פילפולא חריפתא על " + masechet_he
text_whole = {
"title": b + masechet,
"versionTitle": "Vilna Edition",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": text,
"digitizedBySefaria": True,
"license": "Public Domain",
"licenseVetted": True,
"status": "locked",
}
#save
Helper.mkdir_p("preprocess_json/")
saved_commetator = re.sub(" ", "_", commentator.strip())
with open("preprocess_json/"+saved_commetator +"_%s.json" % masechet , 'w') as out:
json.dump(text_whole, out)
def save_texts(main, additions, main_footnotes, added_footnotes):
main_text = {
"title": "Mekhilta DeRabbi Shimon Bar Yochai",
"versionTitle": "Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource": "https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": main,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi.json", 'w') as out:
json.dump(main_text, out)
text_additions = {
"title": "Mekhilta DeRabbi Shimon Bar Yochai Additions",
"versionTitle": "Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource": "https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": additions,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Added.json", 'w') as out:
json.dump(text_additions, out)
main_footnotes_text = {
"versionTitle": "Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource": "https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": main_footnotes,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Footnotes 1.json", 'w') as out:
json.dump(main_footnotes_text, out)
added_footnotes_text = {
"versionTitle": "Mechilta de-Rabbi Simon b. Jochai, Dr. D. Hoffman, Frankfurt 1905",
"versionSource": "https://openlibrary.org/books/OL23318277M/Mekhilta_de-Rabi_Shimon_ben_Yoai_al_sefer_Shemot",
"language": "he",
"text": added_footnotes,
}
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Mekhilta DeRashbi Footnotes 2.json", 'w') as out:
json.dump(added_footnotes_text, out)
def save_parsed_text(text, sub_directory=None):
directory = "preprocess_json/%s" % sub_directory if sub_directory else "preprocess_json"
Helper.mkdir_p(directory)
with open(directory + "/" + text['title'] + ".json", 'w') as out:
json.dump(text, out)
def save_links(links):
Helper.mkdir_p("preprocess_json/links/")
with open("preprocess_json/links/Mekhilta DeRashbi links.json", 'w') as out:
json.dump(links, out)
new_dh = re.sub(ur"\.", " -", DH, count = 1)
else:
new_dh =DH
newLine.append(new_dh)
newDaf.append(newLine)
newShas.append(newDaf)
#except Exception as e:
# print "%s did not work" %mas
#print newShas[3][0][0]
text_whole = {
"title": 'Tosafot' ,
"versionTitle": "Wikisource Tosafot",
"versionSource": "http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": newShas,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Tosafot_on_{}.json".format(mas), 'w') as out:
json.dump(text_whole, out)
#Helper.createBookRecord(book_record())
with open("preprocess_json/Tosafot_on_%s.json" %mas, 'r') as filep:
file_text = filep.read()
mas = re.sub("_"," ", mas.strip())
Helper.postText("Tosafot on {}".format(mas) , file_text, False)
def save_parsed_text(text, sub_directory=None):
directory = "preprocess_json/%s" % sub_directory if sub_directory else "preprocess_json"
Helper.mkdir_p(directory)
with open(directory + "/" + text["title"] + ".json", "w") as out:
json.dump(text, out)
def save_links(links):
Helper.mkdir_p("preprocess_json/links/")
with open("preprocess_json/links/Mekhilta DeRashbi links.json",
'w') as out:
json.dump(links, out)
def save_links(commentator, book_name, links_arr):
Helper.mkdir_p("preprocess_json/mishnahCommentary/links/")
with open("preprocess_json/mishnahCommentary/links/" + book_name + ".json", 'w') as out:
json.dump(links_arr, out)
if "-" not in DH:
new_dh = re.sub(r"\.", " -", DH, count=1)
else:
new_dh = DH
newLine.append(new_dh)
newDaf.append(newLine)
newShas.append(newDaf)
#except Exception as e:
# print "%s did not work" %mas
#print newShas[3][0][0]
text_whole = {
"title": 'Tosafot',
"versionTitle": "Wikisource Tosafot",
"versionSource":
"http://primo.nli.org.il/primo_library/libweb/action/dlDisplay.do?vid=NLI&docId=NNL_ALEPH001300957",
"language": "he",
"text": newShas,
}
#save
Helper.mkdir_p("preprocess_json/")
with open("preprocess_json/Tosafot_on_{}.json".format(mas), 'w') as out:
json.dump(text_whole, out)
#Helper.createBookRecord(book_record())
with open("preprocess_json/Tosafot_on_%s.json" % mas, 'r') as filep:
file_text = filep.read()
mas = re.sub("_", " ", mas.strip())
Helper.postText("Tosafot on {}".format(mas), file_text, False)
def save_parsed_links(links):
Helper.mkdir_p("preprocess_json/links/")
with open("preprocess_json/links/Meshech_Hochma_links.json", 'w') as out:
json.dump(links, out)
def save_parsed_links(links):
Helper.mkdir_p("preprocess_json/links/")
with open("preprocess_json/links/Meshech_Hochma_links.json", 'w') as out:
json.dump(links, out)
def save_links(commentator, book_name, links_arr):
Helper.mkdir_p("preprocess_json/mishnahCommentary/links/")
with open("preprocess_json/mishnahCommentary/links/" + book_name + ".json",
'w') as out:
json.dump(links_arr, out)