-
Notifications
You must be signed in to change notification settings - Fork 4
/
crawler_yt_channel_rest.py
178 lines (163 loc) · 6.96 KB
/
crawler_yt_channel_rest.py
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
169
170
171
172
173
174
175
176
177
178
# -*- coding: utf8 -*-
import requests
<<<<<<< HEAD
import MySQLdb
import sys
import json
=======
import json
import sys
import urllib2
>>>>>>> d5e067f49fdb382e1f58f5c6ad687084a3778f33
#: how to crawl all videos of channel
#: need 2 variables:
#: 1. channelId - store in file channel_ID.txt
#: 2. API key from google console - store in file api_public_key.txt
<<<<<<< HEAD
def channelDetails(data):
'''
sample data:
{
"snippet": {
"playlistId": "UU3djj8jS0370cu_ghKs_Ong",
"thumbnails": {
"default": {
"url": "https://i.ytimg.com/vi/g4TpDfmxZeg/default.jpg",
"width": 120,
"height": 90
},
"high": {
"url": "https://i.ytimg.com/vi/g4TpDfmxZeg/hqdefault.jpg",
"width": 480,
"height": 360
},
"medium": {
"url": "https://i.ytimg.com/vi/g4TpDfmxZeg/mqdefault.jpg",
"width": 320,
"height": 180
},
"maxres": {
"url": "https://i.ytimg.com/vi/g4TpDfmxZeg/maxresdefault.jpg",
"width": 1280,
"height": 720
},
"standard": {
"url": "https://i.ytimg.com/vi/g4TpDfmxZeg/sddefault.jpg",
"width": 640,
"height": 480
}
},
"title": "ABC Song For Children by Hooplakidz",
"resourceId": {
"kind": "youtube#video",
"videoId": "g4TpDfmxZeg"
},
"channelId": "UC3djj8jS0370cu_ghKs_Ong",
"publishedAt": "2015-07-20T12:17:40.000Z",
"channelTitle": "HooplaKidz",
"position": 3,
"description": "Come and sing along to this Brand New ABC Song to teach the alphabets to all you children !! With the tune of Humpty Dumpty nursery rhyme, kids can learn the ABC Alphabet Song in English in a easy and fun way!\n\nHope you enjoyed this new ABC Song on HooplaKidz\nFor more preschool & phonics songs, click here http://www.youtube.com/user/hooplakidz\n\nBe a part of the HooplaKidz family, click below to subscribe to our channel for regular videos! \nhttp://bit.ly/HooplaKidzSubscribe\n\n+ Visit Our Official YouTube Channel! http://www.youtube.com/hooplakidz\n+ Visit our official website! http://www.hooplakidz.com\n+ Follow us on Google Plus! http://bit.ly/hooplakidzgoogleplus\n+ Like our Facebook Fan Page http://bit.ly/HooplaKidzFacebook\n+ Check out our Pinterest Board http://bit.ly/HooplaKidzPinterest\n\nMany thanks to all our HooplaKidz fans for appreciating our videos! \n\nWe would love to hear from you so please do leave your comments and share our videos with your loved ones!\n\nYoBoHo New Media Pvt. Ltd. \u00a9 2015. All rights reserved."
},
"kind": "youtube#playlistItem",
"etag": "\"iDqJ1j7zKs4x3o3ZsFlBOwgWAHU/ajUrnF7ZINf4M6qY6JDqS0Wws9o\"",
"id": "UUCKUM8Hm5dM5OOGUHGO8zeYA_zQpbkX65"
}
for k,v in data.items():
if k.find("thumbnails") != -1:
thumbnails = json.dumps(v)
elif k.find("title") != -1:
title = json.dumps(v)
elif k.find("channelId") != -1:
channelId = json.dumps(v)
elif k.find("publishedAt") != -1:
publishedAt = json.dumps(v)
elif k.find("channelId") != -1:
channelId = json.dumps(v)
elif k.find("description") != -1:
description = json.dumps(v)
elif k.find("resourceId") != -1:
videoId = json.dumps(v["videoId"])
'''
temp = {
"thumbnails_json" : json.dumps(data["thumbnails"]),
=======
# "description" : json.dumps(data["description"]),
#for i in items:
# temp = channelDetails(i["snippet"])
def channelDetails(data):
temp = {
"thumbnails_json" : data["thumbnails"],
>>>>>>> d5e067f49fdb382e1f58f5c6ad687084a3778f33
"title" : data["title"],
"youtubeChannelId" : data["channelId"],
"description" : data["description"],
"streamUrl" : "https://www.youtube.com/watch?v=%s" % data["resourceId"]["videoId"],
"youtubeId" : data["resourceId"]["videoId"],
<<<<<<< HEAD
"catId" : int(sys.argv[-1])
}
#print json.dumps(temp, indent=2)
return temp
with open('/home/hadn/script/api_public_key.txt') as f:
APIkey = f.read().strip()
channelId = sys.argv[1]
print APIkey
url = 'https://www.googleapis.com/youtube/v3/search?order=date&part=snippet&channelId=%s&maxResults=25&key=%s' % (channelId, APIkey)
url = 'https://www.googleapis.com/youtube/v3/channels?part=contentDetails&id=%s&key=%s' % (channelId, APIkey)
#: sql config
#: username: root
#: password: abc@123
db = MySQLdb.connect(host="localhost",user="root", passwd="abc@123",db="alokids", use_unicode=True, charset='utf8')
cursor = db.cursor()
rv = requests.get(url)
playlistId = rv.json()['items'][0]["contentDetails"]["relatedPlaylists"]["uploads"]
count = 1
url = 'https://www.googleapis.com/youtube/v3/playlistItems?part=snippet&playlistId=%s&key=%s' % (playlistId, APIkey)
url_api = "http://localhost/rest/by-yt-id"
while True:
rv = requests.get(url)
temp_rv = rv.json()
items = temp_rv['items']
for i in items:
temp = channelDetails(i["snippet"])
try:
rv = requests.put(url_api, data=temp)
print rv.url
except Exception, e:
print str(e)
pass
nextPageToken = temp_rv["nextPageToken"]
url = 'https://www.googleapis.com/youtube/v3/playlistItems?part=snippet&playlistId=%s&key=%s&pageToken=%s' % (playlistId, APIkey, nextPageToken)
print nextPageToken
print url
db.close()
=======
"catId" : int(sys.argv[-1])
}
return temp
with open('/home/hadn/youtube/script/api_public_key.txt') as f:
APIkey = f.read().strip()
channelId = sys.argv[-2]
url = 'https://www.googleapis.com/youtube/v3/channels?part=contentDetails&id=%s&key=%s' % (channelId, APIkey)
rv = requests.get(url)
playlistId = rv.json()['items'][0]["contentDetails"]["relatedPlaylists"]["uploads"]
url = 'https://www.googleapis.com/youtube/v3/playlistItems?part=snippet&playlistId=%s&key=%s' % (playlistId, APIkey)
print url
url_api = "http://localhost:81/rest/by-yt-id"
url_api = "http://rest.alobet68.com/rest/by-yt-id"
while True:
rv = requests.get(url)
items = rv.json()['items']
for i in items:
temp = channelDetails(i["snippet"])
try:
rest = requests.put(url_api, data=temp)
print rest.text
except Exception, e:
print str(e)
pass
nextPageToken = str(rv.json()['nextPageToken'])
url = 'https://www.googleapis.com/youtube/v3/playlistItems?part=snippet&playlistId=%s&key=%s&pageToken=%s' % (playlistId, APIkey, nextPageToken)
print nextPageToken
print url
>>>>>>> d5e067f49fdb382e1f58f5c6ad687084a3778f33