Spaces:
Runtime error
Runtime error
File size: 16,451 Bytes
9b3b1bc 24de2aa 9b3b1bc 0795ce5 9b3b1bc 0795ce5 9b3b1bc 3588e6d 24de2aa 42ca295 fc51d61 42ca295 0795ce5 fc51d61 3588e6d fc51d61 42ca295 0795ce5 fc51d61 3588e6d b7c28ad 3588e6d fc51d61 42ca295 fc51d61 42ca295 0795ce5 fc51d61 3588e6d 42ca295 fc51d61 0795ce5 fc51d61 3588e6d 42ca295 0795ce5 fc51d61 3588e6d 42ca295 0795ce5 fc51d61 3588e6d fc51d61 42ca295 0795ce5 fc51d61 3588e6d fc51d61 42ca295 fc51d61 0795ce5 fc51d61 3588e6d fc51d61 3588e6d fc51d61 42ca295 fc51d61 24de2aa 0795ce5 24de2aa |
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 |
import requests
from bs4 import BeautifulSoup
from cleantext import clean
import pandas as pd
import numpy as np
onet = pd.read_csv('static/ONET_JobTitles.csv')
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
def remove_new_line(value):
return ''.join(value.splitlines())
def get_onet_code(jobtitle):
onetCode = onet.loc[onet['JobTitle'] == jobtitle, 'onetCode']
onetCode = onetCode.reindex().tolist()[0]
return onetCode
def get_onet_description(onetCode):
url = "https://www.onetonline.org/link/summary/" + onetCode
response = requests.get(url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
jobdescription = soup.p.get_text()
return jobdescription
def get_onet_tasks(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
url = "https://www.onetonline.org/link/result/" + onetCode + "?c=tk&n_tk=0&s_tk=IM&c_tk=0"
response = requests.get(url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('occupations related to multiple tasks')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace("core", " - ").replace("supplemental", "").replace("not available", "").replace(" )importance category task", "").replace(" find ", "")
tasks = tasks.split(". ")
tasks = [''.join(map(lambda c: '' if c in '0123456789-' else c, task)) for task in tasks]
return tasks
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_activities(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
activities_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=wa&n_wa=0&s_wa=IM&c_wa=0"
response = requests.get(activities_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace("importance work activity", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(' ) ', '')])
df = pd.DataFrame(num_desc, columns = ['Importance', 'Activity'])
df = df[df['Importance'] != '']
activities = df
return activities
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_context(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
context_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=cx&n_cx=0&c_cx=0&s_cx=n"
response = requests.get(context_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace("importance work activity", " ")
tasks = tasks.split("? ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df2 = pd.DataFrame(num_desc, columns = ['Importance', 'Condition'])
df2 = df2[df2['Importance'] != '']
context = df2
if len(context.index) < 5:
context_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=wc&n_wc=0&c_wc=0"
response = requests.get(context_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace("importance work activity", " ")
tasks = tasks.split("? ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df2 = pd.DataFrame(num_desc, columns = ['Importance', 'Condition'])
df2 = df2[df2['Importance'] != '']
context = df2
return context
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_skills(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
skills_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=sk&n_sk=0&s_sk=IM&c_sk=0"
response = requests.get(skills_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance skill", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df3 = pd.DataFrame(num_desc, columns = ['Importance', 'Skill'])
df3 = df3[df3['Importance'] != '']
skills = df3
return skills
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_knowledge(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
knowledge_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=kn&n_kn=0&s_kn=IM&c_kn=0"
response = requests.get(knowledge_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance knowledge", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df4 = pd.DataFrame(num_desc, columns = ['Importance', 'Knowledge'])
df4 = df4[df4['Importance'] != '']
knowledge = df4
return knowledge
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_abilities(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
abilities_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=ab&n_ab=0&s_ab=IM&c_ab=0"
response = requests.get(abilities_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
if len(tasks.split('show all show top 10')) > 1:
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance ability", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df5 = pd.DataFrame(num_desc, columns = ['Importance', 'Ability'])
df5 = df5[df5['Importance'] != '']
abilities = df5
return abilities
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_interests(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
interests_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=in&c_in=0"
response = requests.get(interests_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
tasks = tasks.split("occupational interest interest")[1]#.replace('bright outlook', '').replace('updated 2023', '')
if len(tasks.split('back to top')) > 1:
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance interest", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df6 = pd.DataFrame(num_desc, columns = ['Importance', 'Interest'])
df6 = df6[df6['Importance'] != '']
interests = df6
return interests
else:
return pd.DataFrame([("We're sorry."), ("This occupation is currently undergoing updates."), ("Please try again later.")])
def get_onet_values(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
values_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=wv&c_wv=0"
response = requests.get(values_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
tasks = tasks.split('extent work value')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance value", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df7 = pd.DataFrame(num_desc, columns = ['Importance', 'Value'])
df7 = df7[df7['Importance'] != '']
values = df7
return values
def get_onet_styles(onetCode):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
style_url = "https://www.onetonline.org/link/result/" + onetCode + "?c=ws&n_ws=0&c_ws=0"
response = requests.get(style_url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
tasks = str(soup.get_text('reportsubdesc')).replace("reportsubdesc", " ").replace("ImportanceCategoryTask ", "")
tasks = clean(tasks)
tasks = tasks.split('show all show top 10')[1]
tasks = tasks.split('back to top')[0]
tasks = remove_new_line(tasks).replace("related occupations", " ").replace(")importance work style", "").replace(")importance style", " ")
tasks = tasks.split(". ")
split_data = [item.split(" -- ")[0] for item in tasks]
num_desc = []
for i in range(len(tasks)):
temp = [','.join(item) for item in split_data][i].split(',')
num_desc.append([''.join([c for c in temp if c in '0123456789']), ''.join([c for c in temp if c not in '0123456789']).replace(')context work context', '')])
df8 = pd.DataFrame(num_desc, columns = ['Importance', 'Style'])
df8 = df8[df8['Importance'] != '']
styles = df8
return styles
def get_job_postings(onetCode, state):
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.2 Safari/605.1.15'}
url = "https://www.onetonline.org/link/localjobs/" + onetCode + "?st=" + state
response = requests.get(url, headers=headers, verify=False)
soup = BeautifulSoup(response.text, 'html.parser')
jobs = str(soup.get_text("tbody")).split('PostedtbodyTitle and CompanytbodyLocation')[1].split('Sources:')[0].split("tbody")
jobs = jobs[5:45]
starts = np.linspace(start=0, stop=len(jobs)-4,num= 10)
stops = np.linspace(start=3, stop=len(jobs)-1, num= 10)
jobpostings = []
for i in range(0,10):
jobpostings.append(str([' '.join(jobs[int(starts[i]):int(stops[i])])]).replace("['", '').replace("']", ''))
links = str(soup.find_all('a', href=True)).split("</small>")[1].split(', <a href="https://www.careeronestop.org/"')[0].split(' data-bs-toggle="modal" ')
linklist = []
for i in range(1, len(links)):
links[i] = "https://www.onetonline.org" + str(links[i]).split(' role="button">')[0].replace("href=", "")
linklist.append(links[i].replace('"', ''))
return jobpostings, linklist |