|
| 1 | +# for scraping books |
| 2 | +from bs4 import BeautifulSoup as bs |
| 3 | +import requests |
| 4 | +# to identify emoji unicode characters |
| 5 | +import emoji |
| 6 | +import pyfiglet |
| 7 | +import itertools |
| 8 | +import threading |
| 9 | +import time |
| 10 | +import sys |
| 11 | + |
| 12 | + |
| 13 | + |
| 14 | +def is_emoji(text): |
| 15 | + """This function returns True if there is an emoji in the given string else False""" |
| 16 | + return bool(emoji.get_emoji_regexp().search(text)) |
| 17 | + |
| 18 | +def link_to_get(link): |
| 19 | + """This function will get the url of the image & book download direct link using the given link for book download""" |
| 20 | + response = requests.get(link) |
| 21 | + th_html = bs(response.text , "html.parser") |
| 22 | + td_all = th_html.find_all("td" ,id ="info") |
| 23 | + td_all = td_all[0] |
| 24 | + td_a = td_all.find_all("a") |
| 25 | + link_href = td_a[1].get("href") |
| 26 | + img_link_td = td_all.find("img" ,alt="cover") |
| 27 | + img_link_src = img_link_td.get("src") |
| 28 | + img_link = f"http://library.lol{img_link_src}" |
| 29 | + return [link_href, img_link] |
| 30 | + |
| 31 | +def book_get(name, mainres=100, results=5): |
| 32 | + """This function returns the list of books for the given name |
| 33 | + |
| 34 | + You can give in name : |
| 35 | + 1. title of book |
| 36 | + 2. isbn of book |
| 37 | + 3. author of book |
| 38 | + 4. publisher of book |
| 39 | + |
| 40 | + mainres : |
| 41 | + 1. 25 |
| 42 | + 2. 50 |
| 43 | + 3. 100 |
| 44 | + |
| 45 | + Results: |
| 46 | + [ 0.Book Name, |
| 47 | + 1.Author, |
| 48 | + 2.Size, |
| 49 | + 3.Book Type, |
| 50 | + 4.Book Link, |
| 51 | + 5.Book Image Link |
| 52 | + 6.Language]""" |
| 53 | + Books = [] |
| 54 | + if is_emoji(name) == True: |
| 55 | + return "Error: emoji" |
| 56 | + if name == "": |
| 57 | + return "Error: enter name" |
| 58 | + name = name.replace(" ", "+") |
| 59 | + # getting request and response |
| 60 | + url = f"http://libgen.is/search.php?req={name}&lg_topic=libgen&open=0&view=simple&res={mainres}&phrase=1&column=def" |
| 61 | + # print(url) |
| 62 | + response = requests.get(url) |
| 63 | + bs_html = bs(response.text , "html.parser") |
| 64 | + |
| 65 | + if "Search string must contain minimum 3 characters.." in bs_html.body: |
| 66 | + return "Error: Title Too Short" |
| 67 | + |
| 68 | + # scraping the site for response |
| 69 | + table = bs_html.find_all("table") |
| 70 | + table = table[2] |
| 71 | + table_rows = table.find_all("tr") |
| 72 | + a = len(table_rows) |
| 73 | + table_rows.pop(0) |
| 74 | + # print(url, "\n\n") |
| 75 | + if a > 1 : |
| 76 | + counter = 1 |
| 77 | + for i in table_rows : |
| 78 | + if counter <= results: |
| 79 | + # make book list |
| 80 | + book_lst = [] |
| 81 | + # getting all table datas |
| 82 | + table_datas = i.find_all("td") |
| 83 | + # book name |
| 84 | + book_name = table_datas[2].get_text() |
| 85 | + # author name |
| 86 | + author = table_datas[1].get_text() |
| 87 | + # getting link to book |
| 88 | + link_row = table_datas[9] |
| 89 | + a = link_row.find("a" , href = True) |
| 90 | + link = a.get("href") |
| 91 | + # getting image url & direct book download link |
| 92 | + link_all = link_to_get(link) |
| 93 | + # getting language |
| 94 | + language_row = table_datas[6] |
| 95 | + language = language_row.get_text() |
| 96 | + # getting size of book |
| 97 | + size_row = table_datas[7] |
| 98 | + size = size_row.get_text() |
| 99 | + # getting type of book |
| 100 | + type_row = table_datas[8] |
| 101 | + type_ofit = type_row.get_text() |
| 102 | + # this will only take pdfs in English Language |
| 103 | + if (type_ofit != "pdf" and type_ofit != "epub") or language != "English": |
| 104 | + continue |
| 105 | + book_lst.append(book_name) |
| 106 | + book_lst.append(author) |
| 107 | + book_lst.append(size) |
| 108 | + book_lst.append(type_ofit) |
| 109 | + book_lst.append(link_all[0]) |
| 110 | + book_lst.append(link_all[1]) |
| 111 | + book_lst.append(language) |
| 112 | + Books.append(book_lst) |
| 113 | + # print(f"\n\n\n{book_lst}\n\n\n") |
| 114 | + counter+=1 |
| 115 | + if len(Books) >=1 : |
| 116 | + return Books |
| 117 | + else : |
| 118 | + return "Error: no results found" |
| 119 | + else: |
| 120 | + return "Error: no results found" |
| 121 | + |
| 122 | +# a = book_get("Harry Potter",25,5) |
| 123 | +# print(a) |
| 124 | +# for i in a : |
| 125 | +# print(f"\n\nName : {i[0]}\nAuthor : {i[1]}\nSize : {i[2]}\nFormat : {i[3]}\nLink : {i[4]}\nImage : {i[5]}\n\n") |
| 126 | + |
| 127 | +def animate(): |
| 128 | + for c in itertools.cycle(['|', '/', '-', '\\']): |
| 129 | + if done: |
| 130 | + break |
| 131 | + sys.stdout.write('\r...Searching Book ' + c) |
| 132 | + sys.stdout.flush() |
| 133 | + time.sleep(0.1) |
| 134 | + |
| 135 | +if __name__ == "__main__": |
| 136 | + print(pyfiglet.figlet_format("Book Scraper")) |
| 137 | + print("---------------------------------------------------------------") |
| 138 | + print("---------------------------------------------------------------") |
| 139 | + while(True): |
| 140 | + print("\nEnter your Choice: \n1 - Search Book\n2 - Exit") |
| 141 | + entry = int(input()) |
| 142 | + if(entry == 1): |
| 143 | + print("Enter name of book : ") |
| 144 | + book_name = input() |
| 145 | + # loading |
| 146 | + done = False |
| 147 | + #here is the animation |
| 148 | + t = threading.Thread(target=animate) |
| 149 | + t.start() |
| 150 | + books = book_get(book_name, 25, 5) |
| 151 | + done = True |
| 152 | + try: |
| 153 | + for i in books : |
| 154 | + print(f"\n\nName : {i[0]}\nAuthor : {i[1]}\nSize : {i[2]}\nFormat : {i[3]}\nLink : {i[4]}\nImage : {i[5]}\n") |
| 155 | + except: |
| 156 | + if(book_get == "Error: no results found"): |
| 157 | + print("Book not Found/n") |
| 158 | + elif(book_get == "Error: Title Too Short"): |
| 159 | + print("Title too short/n") |
| 160 | + elif(entry == 2): |
| 161 | + print(pyfiglet.figlet_format("Thank You for Using")) |
| 162 | + print("---------------------------------------------------------------") |
| 163 | + print("---------------------------------------------------------------") |
| 164 | + break |
0 commit comments