def book_search(name, author, publisher, destination_folder, force):
# searching Libgen for a book
libgen_url = mirror_checker()
if libgen_url is not None:
br = mechanize.Browser()
br.set_handle_robots(False) # ignore robots
br.set_handle_refresh(False) #
br.addheaders = [('User-agent', 'Firefox')]
br.open(libgen_url)
br.select_form('libgen')
input_form = name + ' ' + author + ' ' + publisher
br.form['req'] = input_form
ac = br.submit()
html_from_page = ac
soup = Soup(html_from_page, 'html.parser')
try:
line_with_epub = epub_finder(soup)
links_with_text = [a['href'] for a in soup.find_all(title="libgen", href=True) if a.text]
Downloading_page = links_with_text[line_with_epub]
print("\nDownloading Link: FOUND")
print(Downloading_page)
nameofbook = file_name(Downloading_page)
if nameofbook is None:
nameofbook = name.replace('\n', '') + author.replace('\n', '') + '.epub'
if force is not True:
decision = input(' * BookCut found "'+nameofbook+'" '
'\nDo you want to download? [Y/n] ')
decision = decision.capitalize()
while decision != "Y" and decision != "N":
decision = input(' * BookCut found "'+nameofbook+'" '
'\nDo you want to download? [Y/n] ')
if decision == "Y":
downloading(Downloading_page, name, author, nameofbook,
destination_folder)
elif decision == "N":
print("\nDownload aborted, try with a different search!")
else:
downloading(Downloading_page, name, author,
nameofbook, destination_folder)
except IndexError:
print("\nDownloading Link: NOT FOUND")
pass
print("================================ \n")
br.close()
else:
print('\nNo mirrors found or bad Internet connection.')
print('Please,try again.')
def test_single_book_download():
title = "Iliad"
author = "Homer"
publisher = " "
type_format = " "
book = Booksearch(title, author, publisher, type_format, mirror_checker())
result = book.search()
extensions = result["extensions"]
print("extensions: ", extensions)
tb = result["table_data"]
mirrors = result["mirrors"]
assert mirrors[0].startswith("http"), "Not correct format of Mirror URL."
assert type(extensions) is list, "Wrong format of extension details."
file_details = book.give_result(extensions, tb, mirrors, extensions[0])
def book(book, author, publisher, destination, extension, forced, md5):
if book == " " and md5 is None:
print("Invalid Input! Check <bookcut book --help> for more.")
elif author != " " and book != " ":
click.echo(
f"\nSearching for {book.capitalize()} by {author.capitalize()}")
elif book != " ":
click.echo(f"\nSearching for {book.capitalize()}")
url = mirror_checker()
if url is not None:
if md5 is not None:
print("\nSearching for book with md5: ", md5)
md5_search(md5, url, destination)
else:
libgen_book_find(book, author, publisher, destination, extension,
forced, url)
def search(self):
url = mirror_checker()
if url is not None:
br = mechanize.Browser()
br.set_handle_robots(False) # ignore robots
br.set_handle_refresh(False) #
br.addheaders = [('User-agent', 'Firefox')]
br.open(url)
br.select_form('libgen')
input_form = self.title + self.author + self.publisher
br.form['req'] = input_form
ac = br.submit()
html_from_page = ac
soup = Soup(html_from_page, 'html.parser')
table = soup.find_all('table')[2]
table_data = []
mirrors = []
extensions = []
for i in table:
j = 0
try:
td = i.find_all('td')
for tr in td:
# scrape mirror links
if j == 9:
temp = tr.find('a', href=True)
mirrors.append(temp['href'])
j = j + 1
row = [tr.text for tr in td]
table_data.append(row)
extensions.append(row[8])
except:
pass
table_details = dict()
table_details['extensions'] = extensions
table_details['table_data'] = table_data
table_details['mirrors'] = mirrors
return table_details
else:
print('\nNo results found or bad Internet connection.')
print('Please,try again.')
def choose_a_book(dataframe):
# asks the user which book to download from the printed DataFrame
if dataframe.empty is False:
dataframe.index += 1
print(dataframe[["Author(s)", "Title", "Size", "Extension"]])
urls = dataframe["Url"].to_list()
titles = dataframe["Title"].to_list()
extensions = dataframe["Extension"].to_list()
choices = []
temp = len(urls) + 1
for i in range(1, temp):
choices.append(str(i))
choices.append("C")
choices.append("c")
try:
while True:
tell_me = str(
input("\n\nPlease enter a number from 1 to {number}"
' to download a book or press "C" to abort'
" search: ".format(number=len(urls))))
if tell_me in choices:
if tell_me == "C" or tell_me == "c":
print("Aborted!")
return None
else:
c = int(tell_me) - 1
filename = titles[c] + "." + extensions[c]
filename = filename_refubrished(filename)
if urls[c].startswith("https://export.arxiv.org/"):
search_downloader(filename, urls[c])
return False
else:
mirror_used = mirror_checker(False)
link = mirror_used + urls[c]
details = link_finder(link, mirror_used)
file_link = details[1]
search_downloader(filename, file_link)
return False
except ValueError:
print(RESULT_ERROR)
print("Please,try again.")
return None
else:
print(RESULT_ERROR)
def booklist_main(file, destination, forced, extension):
"""executes with the command --list"""
Lines = file_list(file)
if Lines is not None:
print("List imported succesfully!")
url = mirror_checker()
if url is not None:
temp = 1
many = len(Lines)
for a in Lines:
if a != "":
print(
f"~[{temp}/{many}] Searching for:",
a,
)
temp = temp + 1
libgen_book_find(a, "", "", destination, extension, forced,
url)
def search(term):
# This function is used when searching to LibGen with the command
# bookcut search -t "keyword"
url = mirror_checker()
if url is not None:
br = mechanize.Browser()
br.set_handle_robots(False) # ignore robots
br.set_handle_refresh(False) #
br.addheaders = [("User-agent", "Firefox")]
br.open(url)
br.select_form("libgen")
input_form = term
br.form["req"] = input_form
ac = br.submit()
html_from_page = ac
soup = Soup(html_from_page, "html.parser")
table = soup.find_all("table")[2]
table_data = []
mirrors = []
extensions = []
for i in table:
j = 0
try:
td = i.find_all("td")
for tr in td:
# scrape mirror links
if j == 9:
temp = tr.find("a", href=True)
mirrors.append(temp["href"])
j = j + 1
row = [tr.text for tr in td]
table_data.append(row)
extensions.append(row[8])
except:
pass
# Clean result page
for j in table_data:
j.pop(0)
del j[8:15]
headers = [
"Author(s)",
"Title",
"Publisher",
"Year",
"Pages",
"Language",
"Size",
"Extension",
]
try:
tabular = pd.DataFrame(table_data)
tabular.index += 1
tabular.columns = headers
print(tabular)
choices = []
temp = len(mirrors) + 1
for i in range(1, temp):
choices.append(str(i))
choices.append("C")
choices.append("c")
while True:
tell_me = str(
input("\n\nPlease enter a number from 1 to {number}"
' to download a book or press "C" to abort'
" search: ".format(number=len(extensions))))
if tell_me in choices:
if tell_me == "C" or tell_me == "c":
print("Aborted!")
return None
else:
c = int(tell_me) - 1
results = [mirrors[c], extensions[c]]
return results
except ValueError:
print("\nNo results found or bad Internet connection.")
print("Please,try again.")
return None
else:
print("\nNo results found or bad Internet connection.")
print("Please,try again.")
def search(term):
# This function is used when searching to LibGen with the command
# bookcut search -t "keyword"
url = mirror_checker()
if url is not None:
br = mechanize.Browser()
br.set_handle_robots(False) # ignore robots
br.set_handle_refresh(False) #
br.addheaders = [('User-agent', 'Firefox')]
br.open(url)
br.select_form('libgen')
input_form = term
br.form['req'] = input_form
ac = br.submit()
html_from_page = ac
soup = Soup(html_from_page, 'html.parser')
table = soup.find_all('table')[2]
table_data = []
mirrors = []
extensions = []
for i in table:
j = 0
try:
td = i.find_all('td')
for tr in td:
# scrape mirror links
if j == 9:
temp = tr.find('a', href=True)
mirrors.append(temp['href'])
j = j + 1
row = [tr.text for tr in td]
table_data.append(row)
extensions.append(row[8])
except:
pass
# Clean result page
for j in table_data:
j.pop(0)
del j[8:15]
headers = [
'Author(s)', 'Title', 'Publisher', 'Year', 'Pages', 'Language',
'Size', 'Extension'
]
try:
tabular = pd.DataFrame(table_data)
tabular.index += 1
tabular.columns = headers
print(tabular)
choices = []
temp = len(mirrors) + 1
for i in range(1, temp):
choices.append(str(i))
choices.append('C')
choices.append('c')
while True:
tell_me = str(
input('\n\nPlease enter a number from 1 to {number}'
' to download a book or press "C" to abort'
' search: '.format(number=len(extensions))))
if tell_me in choices:
if tell_me == 'C' or tell_me == 'c':
print("Aborted!")
return None
else:
c = int(tell_me) - 1
results = [mirrors[c], extensions[c]]
return results
except ValueError:
print('\nNo results found or bad Internet connection.')
print('Please,try again.')
return None
else:
print('\nNo results found or bad Internet connection.')
print('Please,try again.')
def libgen_repo(term):
# Searching LibGen and returns results DataFrame
try:
url = mirror_checker()
if url is not None:
br = mechanize.Browser()
br.set_handle_robots(False) # ignore robots
br.set_handle_refresh(False) #
br.addheaders = [("User-agent", "Firefox")]
br.open(url)
br.select_form("libgen")
input_form = term
br.form["req"] = input_form
ac = br.submit()
html_from_page = ac
html_soup = soup(html_from_page, "html.parser")
table = html_soup.find_all("table")[2]
table_data = []
mirrors = []
extensions = []
for i in table:
j = 0
try:
td = i.find_all("td")
for tr in td:
# scrape mirror links
if j == 9:
temp = tr.find("a", href=True)
mirrors.append(temp["href"])
j = j + 1
row = [tr.text for tr in td]
table_data.append(row)
extensions.append(row[8])
except:
pass
# Clean result page
for j in table_data:
j.pop(0)
del j[8:15]
headers = [
"Author(s)",
"Title",
"Publisher",
"Year",
"Pages",
"Language",
"Size",
"Extension",
]
tabular = pd.DataFrame(table_data)
tabular.columns = headers
tabular["Url"] = mirrors
return tabular
except ValueError:
# create emptyDataframe
df = pd.DataFrame()
return df
def test_mirror_availability():
available_mirror = mirror_checker()
assert type(available_mirror) is str, "Not correct type of LibGen Url"
assert available_mirror.startswith("http"), "Not correct LibGen Url."