generated from wanghaisheng/scrape-app-reviews-without-coding
-
-
Notifications
You must be signed in to change notification settings - Fork 1
/
get_tiktok_ad_recommend.py
217 lines (188 loc) · 8.93 KB
/
get_tiktok_ad_recommend.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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
from unicodedata import category
import requests # Include functionality to make a call to the remote websites
import pandas as pd
import re
import wordninja
import os
import random
import time
#原理初步设想为，假设关键词为jewelry,在instagram中输入"#jewelry",从搜索框的下拉推荐列表中获取扩展关键词
#instagram tag都有一个volume在 但其他的我暂时没想好怎么获取
urls = {
"google": "https://suggestqueries.google.com/complete/search?client=chrome&q=",
# "amazon": "https://completion.amazon.com/search/complete?search-alias=aps&client=amazon-search-ui&mkt=1&q=",
"youtube": "http://suggestqueries.google.com/complete/search?client=firefox&ds=yt&q=",
# "etsy":"https://www.etsy.com/suggestions_ajax.php?extras={"expt":"off","lang":"en-GB","extras":[]}&version=10_12672349415_19&search_type=all&search_query=",
# "instagram":"https://www.instagram.com/web/search/topsearch/?context=blended&include_reel=true&query=%23",
"tiktok":"https://www.tiktok.com/api/search/general/preview/?aid=1988&app_language=en&app_name=tiktok_web&browser_language=en-US&browser_name=Mozilla&browser_online=true&browser_platform=Win32&browser_version=5.0 (Windows)&channel=tiktok_web&cookie_enabled=true&device_id=7034896245308212741&device_platform=web_pc&focus_state=true&from_page=search&history_len=17&is_fullscreen=false&is_page_visible=true&os=windows&priority_region=&referer=®ion=KR&screen_height=840&screen_width=1344&tz_name=Asia/Shanghai&webcast_language=en&keyword="
}
proxies = {
'http': 'socks5://127.0.0.1:1080',
'https': 'socks5://127.0.0.1:1080'
}
def url_ok(url):
try:
response = requests.head(url)
except Exception as e:
# print(f"NOT OK: {str(e)}")
return False
else:
if response.status_code == 200:
# print("OK")
return True
else:
print(f"NOT OK: HTTP response code {response.status_code}")
return False
def rep(m):
s=m.group(1)
return ' '.join(re.split(r'(?=[A-Z])', s))
def get_longtail_keywords_from_recommend(keyword_inputfilename,keyword_outputfilename):
df_queries = pd.read_csv(keyword_inputfilename)
# root.csv will look like below
# keywords (header)
# jewelry
# kids school
# search engine optimization
queries = df_queries.keywords
to_be_saved_queries = []
all_autosuggestions = []
domains = []
for query in queries:
for (domain, url) in urls.items():
print('process',domain,'keyword',query)
# add the query to the url
remote_url = url + query
# print(f"Remote url : {remote_url}")
headers = {'User-Agent': 'User-Agent: Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:80.0) Gecko/20100101 Firefox/80.0'}
response=''
if url_ok('http://www.google.com'):
# print('network is fine,there is no need for proxy ')
response = requests.get(remote_url).json()
else:
# print('google can not be access ')
# print('we need for proxy ',proxies)
response = requests.get(remote_url,proxies=proxies).json()
# print(response)
auto_suggest=[]
if domain=='etsy':
for item in response['results']:
if "</span>" in item['query']:
pass
else:
if query==item['query']:
pass
else:
auto_suggest.append(item['query'])
elif domain in ['google','youtube','amazon']:
if query in response[1]:
response[1].remove(query)
auto_suggest = response[1]
# print(response[1])
elif domain =='tiktok':
# print(response)
for item in response['sug_list']:
# print(item['content'])
if query==item['content']:
pass
else:
auto_suggest.append(item['content'])
elif domain=='instagram':
for item in response['hashtags']:
k = ' '.join(wordninja.split(item['hashtag']['name']))
if query==k:
pass
else:
auto_suggest.append(k)
item['hashtag']['media_count']
# print(auto_suggest)
auto_suggest = [ii for n,ii in enumerate(auto_suggest) if ii not in auto_suggest[:n]]
for suggestion in auto_suggest:
to_be_saved_queries.append(query)
all_autosuggestions.append(suggestion)
domains.append(domain)
time.sleep(random.randint(3, 10))
df = pd.DataFrame({"domain": domains, "query": to_be_saved_queries, "keywords": all_autosuggestions})
df.to_csv(keyword_outputfilename, mode='a', index=False)
async def get_longtail_keywords_from_one(query):
# root.csv will look like below
# keywords (header)
# jewelry
# kids school
# search engine optimization
to_be_saved_queries = []
all_autosuggestions = []
domains = []
for (domain, url) in urls.items():
print('process',domain,'keyword',query)
# add the query to the url
remote_url = url + query
# print(f"Remote url : {remote_url}")
headers = {'User-Agent': 'User-Agent: Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:80.0) Gecko/20100101 Firefox/80.0'}
response=''
if url_ok('http://www.google.com'):
# print('network is fine,there is no need for proxy ')
response = requests.get(remote_url).json()
else:
# print('google can not be access ')
# print('we need for proxy ',proxies)
response = requests.get(remote_url,proxies=proxies).json()
# print(response)
auto_suggest=[]
if domain=='etsy':
for item in response['results']:
if "</span>" in item['query']:
pass
else:
if query==item['query']:
pass
else:
auto_suggest.append(item['query'])
elif domain in ['google','youtube','amazon']:
if query in response[1]:
response[1].remove(query)
auto_suggest = response[1]
# print(response[1])
elif domain =='tiktok':
# print(response)
for item in response['sug_list']:
# print(item['content'])
if query==item['content']:
pass
else:
auto_suggest.append(item['content'])
elif domain=='instagram':
for item in response['hashtags']:
k = ' '.join(wordninja.split(item['hashtag']['name']))
if query==k:
pass
else:
auto_suggest.append(k)
item['hashtag']['media_count']
# print(auto_suggest)
auto_suggest = [ii for n,ii in enumerate(auto_suggest) if ii not in auto_suggest[:n]]
for suggestion in auto_suggest:
to_be_saved_queries.append(query)
all_autosuggestions.append(suggestion)
domains.append(domain)
time.sleep(random.randint(3, 10))
# df = pd.DataFrame({"domain": domains, "query": to_be_saved_queries, "keywords": all_autosuggestions})
# df.to_csv(outputfilename, mode='a', index=False)
return all_autosuggestions
if __name__ == "__main__":
for root, dirs, files in os.walk('.'):
for name in files:
if name.endswith('-lv0.csv'):
category=name.split('-')[0]
print('========',category)
# category='jewelry'
category_root_keyword=category+'-lv0.csv'
category_level_1_keyword=category+'-lv1.csv'
category_level_2_keyword=category+'-lv2.csv'
category_level_3_keyword=category+'-lv3.csv'
category_level_4_keyword=category+'-lv4.csv'
category_level_5_keyword=category+'-lv5.csv'
get_longtail_keywords_from_recommend(category_root_keyword,category_level_1_keyword)
get_longtail_keywords_from_recommend(category_level_1_keyword,category_level_2_keyword)
get_longtail_keywords_from_recommend(category_level_2_keyword,category_level_3_keyword)
get_longtail_keywords_from_recommend(category_level_3_keyword,category_level_4_keyword)
get_longtail_keywords_from_recommend(category_level_4_keyword,category_level_5_keyword)