deepvid.py

   1 #!/bin/env python
   2 """
   3 Deepvid Copyright Mikolaj 'lich' Halber 2016
   4 """
   5 from urllib import request, error
   6 import random
   7 import string
   8 import os
   9 import json
  10 import sqlite3 as sdb
  11 from sys import argv
  12
  13 def baseinit(basefile='deepvid.db'):
  14     conn = sdb.connect(basefile)
  15     curr = conn.cursor()
  16     curr.execute("CREATE TABLE IF NOT EXISTS Videos(ID TEXT, Title TEXT, Views INT, Link TEXT)")
  17
  18 def baseadd(data, basefile='deepvid.db'):
  19     conn = sdb.connect(basefile)
  20     curr=conn.cursor()
  21     data.append('https://youtu.be/' + data[0])
  22     curr.execute("INSERT INTO Videos VALUES (?, ?, ?, ?)", tuple(data))
  23     conn.commit()
  24
  25 def random_char(length):
  26     """Pretty simple function for getting random strings"""
  27     return ''.join(random.choice(string.ascii_letters) for x in range(length))
  28
  29 def links(key_loc, iterations, no_next_page):
  30     """Gets links for videos under 20 views"""
  31     old_queries = []
  32     good_vids = []
  33     baseinit()
  34     with open(key_loc, 'r') as myfile:
  35         key = myfile.read().replace('\n', '')
  36     next_page = 0
  37     data = ""
  38     for just_dont_use_this_var in range(0, iterations):
  39         #does the search $iterations number of times
  40         if not next_page or no_next_page:
  41             #check if next page was chosen
  42             query = random_char(4)
  43             nxt_pg_tok = ""
  44             if query in old_queries:
  45                 continue
  46             else:
  47                 old_queries.append(query)
  48         else:
  49             nxt_pg_tok = "&pageToken={}".format(data["nextPageToken"])
  50         link = "https://www.googleapis.com/youtube/v3/search" \
  51                "?part=snippet&type=video&q={}&key={}&order=date&maxResults=50{}".format( \
  52                 query, key, nxt_pg_tok)
  53         try:
  54             req = request.urlopen(link).read().decode('utf-8')
  55             data = json.loads(req)
  56         except error.HTTPError:
  57             continue
  58         if "nextPageToken" in data:
  59             next_page = 1 #check for next page token
  60         else:
  61             next_page = 0
  62         if data["pageInfo"]["totalResults"] == 0:
  63             continue
  64         for i in data["items"]:
  65             if i["id"]["videoId"] in good_vids:
  66                 continue #throw away videos that were already found
  67             v_link = "https://www.googleapis.com/youtube/v3/videos" \
  68                      "?part=statistics&id={}&key={}".format(i["id"]["videoId"], key)
  69             v_req = request.urlopen(v_link).read().decode('utf-8')
  70             v_data = json.loads(v_req)
  71             if int(v_data["items"][0]["statistics"]["viewCount"]) <= 20:
  72                 good_vids.append(v_data["items"][0]["id"])
  73                 baseadd([i["id"]["videoId"], i["snippet"]["title"], \
  74                         int(v_data["items"][0]["statistics"]["viewCount"])])
  75             else:
  76                 continue
  77     return 0
  78
  79 def main():
  80     """Main function"""
  81     print(links(argv[1], 150, True))
  82 if __name__ == '__main__':
  83     main()