libgen_script.py

import urllib.parse
import urllib.request

BASE_URL = 'http://libgen.rs/search.php'

def libgen_post_request(query, pagenumber):
    url_encoded_query = urllib.parse.urlencode({'req':query})
    extra_params = '&open=0&res=25&view=simple&phrase=1&column=def&res=100'
    libgen_current_page = f'&page={pagenumber}'
    full_url = f'{BASE_URL}?{url_encoded_query}{extra_params}{libgen_current_page}'
    req = urllib.request.Request(full_url)

    with urllib.request.urlopen(req) as response:
        the_page_bytes = response.read()
        the_page_str = the_page_bytes.decode('utf')

    return the_page_str

def libgen_response_grabber(query):
    pagenumber = 1
    end_pagination_flag = True
    while end_pagination_flag:
        good_line_flag = False
        for line in libgen_post_request(query, pagenumber).splitlines():
            if good_line_flag:
                print(line)
                continue

            if line.startswith("<table width=100%><tr><td align='left' width=45%><font color=grey size=1>"):
                if '>0 files found<' in line:
                    end_pagination_flag = False
                    break

                showing_results_str = line.split('|')[1].split('<')[0].strip()
                print(showing_results_str)
                range_of_results = showing_results_str.replace('showing results from ', '').replace('to', '')
                first, last = range_of_results.split()

                if int(first) > int(last):
                    end_pagination_flag = False
                else:
                    print(line)
                    good_line_flag = True

        pagenumber +=1


if __name__ == '__main__':
    libgen_response_grabber('the black swan')