-
-
Notifications
You must be signed in to change notification settings - Fork 37
/
Copy pathdeviantart_fetch.py
executable file
·291 lines (236 loc) · 8.09 KB
/
deviantart_fetch.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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
#!/usr/bin/env python
"""
This file is dedicated to querying data from the DeviantArt API.
"""
# Standard library
import argparse
import csv
import os
import sys
import traceback
# Third-party
import pandas as pd
import requests
import yaml
from dotenv import load_dotenv
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
# Add parent directory so shared can be imported
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
# First-party/Local
import shared # noqa: E402
# Setup
LOGGER, PATHS = shared.setup(__file__)
# Load environment variables
load_dotenv(PATHS["dotenv"])
# Global Variable for API_KEYS indexing
API_KEYS_IND = 0
# Gets API_KEYS and PSE_KEY from .env file
API_KEYS = os.getenv("GOOGLE_API_KEYS").split(",")
PSE_KEY = os.getenv("PSE_KEY")
# Log the start of the script execution
LOGGER.info("Script execution started.")
def parse_arguments():
"""
Parses command-line arguments, returns parsed arguments.
"""
LOGGER.info("Parsing command-line arguments")
parser = argparse.ArgumentParser(
description="DeviantArt Data Fetching Script"
)
parser.add_argument(
"--licenses", type=int, default=10, help="Number of licenses to query"
)
return parser.parse_args()
def set_up_data_file():
"""
Sets up the data file for recording results.
"""
LOGGER.info("Setting up the data file for recording results.")
header = "LICENSE TYPE,Document Count\n"
with open(
os.path.join(PATHS["data_phase"], "deviantart_fetched.csv"), "w"
) as f:
f.write(header)
def get_license_list():
"""
Provides the list of licenses from Creative Commons.
Returns:
list: A list containing all license types that should be searched.
"""
LOGGER.info("Retrieving list of licenses from Creative Commons' record.")
cc_license_data = pd.read_csv(
os.path.join(PATHS["repo"], "legal-tool-paths.txt"), header=None
)
license_pattern = r"((?:[^/]+/){2}(?:[^/]+)).*"
license_list = (
cc_license_data[0]
.str.extract(license_pattern, expand=False)
.dropna()
.unique()
)
return license_list
def get_request_url(license_type):
"""
Provides the API Endpoint URL for a specified license type.
Args:
license_type: A string representing the type of license.
Returns:
str: The API Endpoint URL for the query specified by parameters.
"""
LOGGER.info(f"Generating API Endpoint URL for license: {license_type}")
try:
api_key = API_KEYS[API_KEYS_IND]
return (
"https://customsearch.googleapis.com/customsearch/v1"
f"?key={api_key}&cx={PSE_KEY}"
"&q=_&relatedSite=deviantart.com"
f'&linkSite=creativecommons.org{license_type.replace("/", "%2F")}'
)
except IndexError:
LOGGER.error("Depleted all API Keys provided")
raise shared.QuantifyingException("No API keys left to use", 1)
def get_response_elems(license_type):
"""
Retrieves the number of documents for the specified license type.
Args:
license_type: A string representing the type of license.
Returns:
dict: A dictionary containing the total document count.
"""
LOGGER.info(f"Querying metadata for license: {license_type}")
try:
request_url = get_request_url(license_type)
max_retries = Retry(
total=5,
backoff_factor=10,
status_forcelist=[403, 408, 500, 502, 503, 504],
)
session = requests.Session()
session.mount("https://", HTTPAdapter(max_retries=max_retries))
with session.get(request_url) as response:
response.raise_for_status()
search_data = response.json()
return {
"totalResults": search_data["searchInformation"]["totalResults"]
}
except requests.exceptions.HTTPError as e:
global API_KEYS_IND
API_KEYS_IND += 1
LOGGER.error(f"HTTP Error: {e}. Switching to the next API key.")
if API_KEYS_IND < len(API_KEYS):
return get_response_elems(license_type)
else:
raise shared.QuantifyingException(
f"HTTP Error: {e}. No API keys left.", 1
)
except requests.RequestException as e:
LOGGER.error(f"Request Exception: {e}")
raise shared.QuantifyingException(f"Request Exception: {e}", 1)
except KeyError as e:
LOGGER.error(f"KeyError: {e}.")
raise shared.QuantifyingException(f"KeyError: {e}", 1)
def retrieve_license_data(args):
"""
Retrieves the data of all license types specified.
Args:
args: Parsed command-line arguments.
Returns:
int: The total number of documents retrieved.
"""
LOGGER.info("Retrieving the data for all license types.")
licenses = get_license_list()[: args.licenses]
# data = []
total_docs_retrieved = 0
for license_type in licenses:
data_dict = get_response_elems(license_type)
total_docs_retrieved += int(data_dict["totalResults"])
record_results(license_type, data_dict)
return total_docs_retrieved
def record_results(license_type, data):
"""
Records the data for a specific license type into the CSV file.
Args:
license_type: The license type.
data: A dictionary containing the data to record.
"""
LOGGER.info(f"Recording data for license: {license_type}")
row = [license_type, data["totalResults"]]
with open(
os.path.join(PATHS["data_phase"], "deviantart_fetched.csv"),
"a",
newline="",
) as f:
writer = csv.writer(f, dialect="unix")
writer.writerow(row)
def load_state():
"""
Loads the state from a YAML file, returns the last recorded state.
Returns:
dict: The last recorded state.
"""
if os.path.exists(PATHS["state"]):
with open(PATHS["state"], "r") as f:
return yaml.safe_load(f)
return {"total_records_retrieved (deviantart)": 0}
def save_state(state: dict):
"""
Saves the state to a YAML file.
Args:
state: The state dictionary to save.
"""
with open(PATHS["state"], "w") as f:
yaml.safe_dump(state, f)
def main():
# Fetch and merge changes
shared.fetch_and_merge(PATHS["repo"])
args = parse_arguments()
state = load_state()
total_docs_retrieved = state["total_records_retrieved (deviantart)"]
LOGGER.info(f"Initial total_records_retrieved: {total_docs_retrieved}")
goal_documents = 1000 # Set goal number of documents
if total_docs_retrieved >= goal_documents:
LOGGER.info(
f"Goal of {goal_documents} documents already achieved."
" No further action required."
)
return
# Log the paths being used
shared.paths_log(LOGGER, PATHS)
# Create data directory for this phase
os.makedirs(PATHS["data_phase"], exist_ok=True)
if total_docs_retrieved == 0:
set_up_data_file()
# Retrieve and record data
docs_retrieved = retrieve_license_data(args)
# Update the state with the new count of retrieved records
total_docs_retrieved += docs_retrieved
LOGGER.info(
f"Total documents retrieved after fetching: {total_docs_retrieved}"
)
state["total_records_retrieved (deviantart)"] = total_docs_retrieved
save_state(state)
# Add and commit changes
shared.add_and_commit(
PATHS["repo"], PATHS["data_quarter"], "Add and commit DeviantArt data"
)
# Push changes
shared.push_changes(PATHS["repo"])
if __name__ == "__main__":
try:
main()
except shared.QuantifyingException as e:
if e.exit_code == 0:
LOGGER.info(e.message)
else:
LOGGER.error(e.message)
sys.exit(e.exit_code)
except SystemExit as e:
LOGGER.error(f"System exit with code: {e.code}")
sys.exit(e.code)
except KeyboardInterrupt:
LOGGER.info("(130) Halted via KeyboardInterrupt.")
sys.exit(130)
except Exception:
LOGGER.exception(f"(1) Unhandled exception: {traceback.format_exc()}")
sys.exit(1)