File size: 5,990 Bytes
340cbde |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
from youtube import proto
from youtube import utils
from flask import Markup
import urllib.parse
import requests
import base64
import json
def page_number_to_sp_parameter(page, autocorrect, sort, filters):
offset = (int(page) - 1)*20 # 20 results per page
autocorrect = proto.nested(8, proto.uint(1, 1 - int(autocorrect) ))
filters_enc = proto.nested(2, proto.uint(1, filters['time']) + proto.uint(2, filters['type']) + proto.uint(3, filters['duration']))
result = proto.uint(1, sort) + filters_enc + autocorrect + proto.uint(9, offset) + proto.string(61, b'')
return base64.urlsafe_b64encode(result).decode('ascii')
def search_by_terms(search_terms, page, autocorrect, sort, filters):
url = "https://www.youtube.com/results?search_query=" + urllib.parse.quote_plus(search_terms)
headers = {
'Host': 'www.youtube.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)',
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'X-YouTube-Client-Name': '1',
'X-YouTube-Client-Version': '2.20180418',
}
url += "&pbj=1&sp=" + page_number_to_sp_parameter(page, autocorrect, sort, filters).replace("=", "%3D")
content = requests.get(url, headers=headers).text
info = json.loads(content)
videos = get_videos_from_search(info)
channels = get_channels_from_search(info)
results = {
"videos": videos,
"channels": channels
}
return results
def get_channels_from_search(search):
results = []
search = search[1]['response']
primaryContents = search['contents']['twoColumnSearchResultsRenderer']['primaryContents']
contents = primaryContents['sectionListRenderer']['contents']
for content in contents:
try:
items = content['itemSectionRenderer']['contents']
except:
continue
for item in items:
try:
item['channelRenderer']
channel = get_channel_renderer_item_info(item['channelRenderer'])
results.append(channel)
except KeyError:
continue
return results
def get_channel_renderer_item_info(item):
try:
suscribers = item['subscriberCountText']['simpleText'].split(" ")[0]
except:
suscribers = "?"
try:
description = utils.get_description_snippet_text(item['descriptionSnippet']['runs'])
except KeyError:
description = ""
try:
channel = {
"channelId": item['channelId'],
"username": item['title']['simpleText'],
"thumbnail": "https:{}".format(item['thumbnail']['thumbnails'][0]['url'].replace("/", "~")),
"description": Markup(str(description)),
"suscribers": suscribers,
"videos": item['videoCountText']['runs'][0]['text']
}
except KeyError:
channel = {
"channelId": item['channelId'],
"username": item['title']['simpleText'],
"avatar": item['thumbnail']['thumbnails'][0]['url'],
"suscribers": suscribers
}
return channel
def get_videos_from_search(search):
latest = []
results = []
search = search[1]['response']
primaryContents = search['contents']['twoColumnSearchResultsRenderer']['primaryContents']
contents = primaryContents['sectionListRenderer']['contents']
for content in contents:
try:
items = content['itemSectionRenderer']['contents']
except:
continue
for item in items:
try:
item['videoRenderer']
video = get_video_renderer_item_info(item['videoRenderer'])
results.append(video)
except KeyError:
continue
# Sometimes Youtube will return an empty query. Try again.
return results
def get_video_renderer_item_info(item):
published = ""
views = ""
isLive = False
isUpcoming = False
thumbnailOverlays = item['thumbnailOverlays']
try:
if 'UPCOMING' in str(thumbnailOverlays):
start_time = item['upcomingEventData']['startTime']
isUpcoming = True
views = "-"
published = "Scheduled"
except KeyError:
isUpcoming = False
try:
if 'LIVE' in str(thumbnailOverlays):
isLive = True
try:
views = item['viewCountText']['simpleText']
except:
views = "Live"
try:
duration = item['lengthText']['simpleText']
except:
duration = "-"
if published != "Scheduled":
try:
published = item['publishedTimeText']['simpleText']
except KeyError:
published = "None"
except:
isUpcoming = False
isLive = False
if not isUpcoming and not isLive:
views = item['viewCountText']['simpleText']
published = item['publishedTimeText']['simpleText']
duration = item['lengthText']['simpleText']
video = {
'videoTitle':item['title']['runs'][0]['text'],
'description':Markup(str(utils.get_description_snippet_text(item['descriptionSnippet']['runs']))),
'views':views,
'timeStamp':published,
'duration':duration,
'channelName':item['ownerText']['runs'][0]['text'],
'authorUrl':"/channel/{}".format(item['ownerText']['runs'][0]['navigationEndpoint']['browseEndpoint']['browseId']),
'channelId':item['ownerText']['runs'][0]['navigationEndpoint']['browseEndpoint']['browseId'],
'id':item['videoId'],
'videoUrl':f"/watch?v={item['videoId']}",
'isLive':isLive,
'isUpcoming':isUpcoming,
'videoThumb':item['thumbnail']['thumbnails'][0]['url'],
}
return video
|