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
|
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Convert MSC HTML to CSV\n",
"\n",
"- create name lists"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%reload_ext autoreload\n",
"%autoreload 2\n",
"\n",
"from os.path import join\n",
"from pathlib import Path\n",
"from functools import partial\n",
"from multiprocessing.dummy import Pool as ThreadPool\n",
"\n",
"import lxml\n",
"from bs4 import BeautifulSoup\n",
"import urllib.request\n",
"from tqdm import tqdm_notebook as tqdm\n",
"import pandas as pd\n",
"\n",
"import sys\n",
"sys.path.append('/work/megapixels_dev/megapixels/')\n",
"from app.settings import app_cfg as cfg\n",
"from app.utils import file_utils, im_utils"
]
},
{
"cell_type": "code",
"execution_count": 147,
"metadata": {},
"outputs": [],
"source": [
"fp_dir_in = '/data_store/datasets/munich_security_conference/participants/'\n",
"fp_dir_out = '/data_store/datasets/munich_security_conference/participants/'\n",
"fp_out_all_csv = join(fp_dir_ou, 'participants.csv') # total list\n",
"years = ['2009', '2010', '2011', '2014']"
]
},
{
"cell_type": "code",
"execution_count": 143,
"metadata": {},
"outputs": [],
"source": [
"def parse_name(name):\n",
" try:\n",
" ridx = name.rindex(',')\n",
" except Exception as e:\n",
" # names like \"Ban Ki-moon\" have no comman\n",
" if name == 'Ban Ki-moon':\n",
" name = 'Ki-moon, Ban'\n",
" elif name == 'Fu Ying':\n",
" name = 'Ying, Fu'\n",
" elif name == 'Dr. Ng Eng Hen':\n",
" # unclear: https://en.wikipedia.org/wiki/Ng_Eng_Hen\n",
" name = 'Ng, Dr. Eng Hen' \n",
" elif name == 'Seok-soo Lee':\n",
" name = 'Lee, Seok-soo'\n",
" else:\n",
" print(f'Could not handle: \"{name}\"')\n",
" ridx = name.rindex(',')\n",
" \n",
" name_last = name[:ridx].strip()\n",
" name_first = name[(ridx + 1):].strip()\n",
" return name_first, name_last\n",
" \n",
"def parse_year(fp_in_html, year):\n",
" # create soup\n",
" with open(fp_in_html, 'r') as fp:\n",
" data = fp.read()\n",
" soup = BeautifulSoup(data, 'lxml')\n",
" \n",
" # get rows\n",
" table = soup.find('table', attrs={'class':'contenttable'})\n",
" tbody = table.find('tbody')\n",
" trows = tbody.find_all('tr')\n",
" \n",
" # parse by year\n",
" participants = []\n",
" for trow in trows[1:]:\n",
" if year == '2009' or year == '2014':\n",
" tds = trow.find_all('td')\n",
" name = tds[0].text.strip()\n",
" name_first, name_last = parse_name(name)\n",
" desc = tds[1].text.strip()\n",
" elif year == '2010':\n",
" tds = trow.find_all('td')\n",
" name_first = tds[0].text.strip()\n",
" name_last = tds[1].text.strip()\n",
" desc = tds[2].text.strip()\n",
" elif year == '2011':\n",
" tds = trow.find_all('td')\n",
" name = tds[0].find_all('p')[0].text.strip()\n",
" name_first, name_last = parse_name(name)\n",
" desc = tds[1].find_all('p')[0].text.strip()\n",
" \n",
" obj = {'name_first': name_first, 'name_last': name_last, 'description': desc, 'year': year}\n",
" participants.append(obj)\n",
" \n",
" return participants"
]
},
{
"cell_type": "code",
"execution_count": 148,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2009\n",
"Wrote: /data_store/datasets/munich_security_conference/participants/2009.csv with 346 items\n",
"2010\n",
"Wrote: /data_store/datasets/munich_security_conference/participants/2010.csv with 317 items\n",
"2011\n",
"Wrote: /data_store/datasets/munich_security_conference/participants/2011.csv with 341 items\n",
"2014\n",
"Wrote: /data_store/datasets/munich_security_conference/participants/2014.csv with 467 items\n",
"Wrote: /data_store/datasets/munich_security_conference/participants/participants.csv with 1471 items\n"
]
}
],
"source": [
"participants_all = []\n",
"for year in years:\n",
" fp_in_html = join(fp_dir_out, f'{year}.html')\n",
" fp_out_csv = join(fp_dir_out, f'{year}.csv')\n",
" participants = parse_year(fp_in_html, year)\n",
" participants_all += participants\n",
" df = pd.DataFrame.from_dict(participants)\n",
" df.to_csv(fp_out_csv, index=False)\n",
" print(f'Wrote: {fp_out_csv} with {len(participants)} items')\n",
"\n",
"# write total list\n",
"\n",
"df = pd.DataFrame.from_dict(participants_all)\n",
"df.to_csv(fp_out_all_csv, index=False)\n",
"print(f'Wrote: {fp_out_all_csv} with {len(participants_all)} items')"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 95,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "megapixels",
"language": "python",
"name": "megapixels"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|
