Spaces:
Runtime error
Runtime error
File size: 13,756 Bytes
05ab1ec e9ebb6e 05ab1ec e9ebb6e 05ab1ec e9ebb6e 05ab1ec e9ebb6e 05ab1ec 01ef47d 05ab1ec e9ebb6e 05ab1ec |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 |
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, parse_qs
from utils import isValidURL
from nlp import summarizer
import json
import sys
import os
# REQUIREMENTS: https://pixeltree.notion.site/City-Council-Scraping-34a2f5a24d59400faf9a128f2653ebf2
# Meeting Minutes Directory: https://pub-calgary.escribemeetings.com
# INPUT (arg 1): Valid URL pointing to meeting minutes. Needs to be wrapped in quotes
# OPTIONAL INPUT (arg 2): Output directory
# OUTPUT: JSON document containing required information scraped from input URL
# Debug mode
DEBUG = False
if __name__ == "__main__":
DEBUG = True
def minutes_scraper(URL=""):
if not isValidURL(URL):
print("Invalid or missing URL input")
print("Please enter a URL now:")
return "Invalid URL"
# Get output directory
out_dir = ""
out_dir = os.getcwd()
###
s = summarizer() # Summarizer object
# Object to be seriliazed
JSON_obj = {}
# Get meeting ID
page = requests.get(URL)
o = urlparse(URL)
query = parse_qs(o.query)
JSON_obj["meeting_id"] = query["Id"][0]
# Complete HTML File
soup = BeautifulSoup(page.content, "html.parser")
# Most of the page content is found in this container
page_content = soup.find(id="package-container")
###
# MM Header
agenda_header = page_content.find("header", class_="AgendaHeader")
## Header information
# Get the Agenda Header
try:
JSON_obj["agenda_header_subtitle"] = agenda_header.find("p", class_="AgendaHeaderSubTitle").text
except AttributeError:
JSON_obj["agenda_header_subtitle"] = ""
# Get the start time
JSON_obj["start_time"] = agenda_header.find("time").text
# Get the location
try:
JSON_obj["location"] = agenda_header_subtitle = agenda_header.find("div", class_="Value LocationValue").text ### This does not get all location info
except AttributeError:
JSON_obj["location"] = ""
# Get the attendence (seperated by who can and can't vote)
attendance_table = agenda_header.find(class_="AgendaHeaderAttendanceTable").find_all("div")
try:
present = [x.text for x in attendance_table[2].find_all("li")]
except IndexError:
present = []
try:
also_present = [x.text for x in attendance_table[5].find_all("li")]
except IndexError:
also_present = []
JSON_obj["attendance"] = {'present': present, 'also_present': also_present}
###
# MM Body
agenda_items = page_content.find("div", class_="AgendaItems")
## Body information
# Get item containers
agenda_item_containers = agenda_items.find_all("div", class_="AgendaItemContainer indent")
# Get roll call
try:
roll_call = agenda_item_containers[0].find_all("p", class_="Body1")
JSON_obj["roll_call"] = roll_call[2].text.rstrip('.').replace(', and ', ', ').split(', ')
except IndexError:
JSON_obj["roll_call"] = []
if DEBUG:
print(JSON_obj["roll_call"])
# Get generator of item containers
agenda_item_containers = agenda_items.children
item_number = 1
for agenda_item in agenda_item_containers:
# Get titles
titles = [x.text for x in agenda_item.find_all("div", class_="AgendaItemTitle")]
# Get each motion in each item
motions = agenda_item.find_all("ul", class_="AgendaItemMotions")
if DEBUG:
print(item_number)
if motions != None:
item_sub_number = 1
for motion in motions:
# Dictionary to store all motion info
motion_obj = {}
if DEBUG:
print(str(item_number) + '.' + str(item_sub_number))
# Place "anchor"
motion_anchor = [x.parent.parent.parent.parent for x in motion.find_all("div", class_="MotionText RichText")]
# Get motion title
motion_titles = [x.find("div", class_="AgendaItemTitle").text.strip() for x in motion_anchor]
# Get list of who the motion is moved by
moved_by_list = [x.find("span", class_="Value") for x in motion.find_all("div", class_="MovedBy")]
moved_by_list = [x.text for x in moved_by_list]
# Get motion description
motion_description_list = [x.text for x in motion.find_all("div", class_="MotionText RichText")]
# Get motion result
motion_result_list = [x.text for x in motion.find_all("div", class_="MotionResult")]
# Get motion votes
motion_votes_list = [x.text[x.text.find(')') + 1:].split(', and ') for x in motion.find_all("table", class_="MotionVoters")]
# Get motion attachments
motion_attachments_list = [x.find_all("a", class_="Link") for x in motion_anchor]
motion_attachments_list_names = []
motion_attachments_list_links = []
for x in motion_attachments_list:
motion_attachments_list_names.append([y.text for y in x]) # ?
motion_attachments_list_links.append([y['href'] for y in x])
motion_obj["titles"] = motion_titles
motion_obj["moved_by"] = moved_by_list
motion_obj["details"] = motion_description_list
motion_obj["results"] = motion_result_list
motion_obj["votes"] = motion_votes_list
motion_obj['attachment_names'] = motion_attachments_list_names[0]
motion_obj['attachment_links'] = motion_attachments_list_links[0]
motion_obj['attachment_count'] = len(motion_attachments_list_names[0])
for desc in motion_description_list:
if len(desc.split()) > s.max_length:
motion_obj['summary'] = s.summarize(text=desc)[0]
else:
motion_obj['summary'] = "Too short to summarize"
if DEBUG:
print(str(item_number) + '.' + str(item_sub_number))
print(motion_titles) # title
print("Moved by: " + str(moved_by_list)) # Moved by
print(motion_description_list) # Other details
print("Result: " + str(motion_result_list)) # Result
print("Votes: " + str(motion_votes_list)) # Votes
print(motion_attachments_list_names[0]) # attachment names
print(motion_attachments_list_links[0]) # attachment links
print()
# Append to JSON object
JSON_obj[f'{item_number}.{item_sub_number}'] = motion_obj
item_sub_number+=1
if DEBUG:
print('-----------------------------------\n\n\n')
item_number+=1
# # Serialize and write to "meeting_minutes.json"
# with open(f"{out_dir}/meeting_minutes.json", "w") as out:
# json.dump(JSON_obj, out, indent=4)
# Add this to data base
return JSON_obj
def minutes_scraper_no_sum(URL=""):
if not isValidURL(URL):
print("Invalid or missing URL input")
print("Please enter a URL now:")
return "Invalid URL"
# Get output directory
out_dir = ""
out_dir = os.getcwd()
###
s = summarizer() # Summarizer object
# Object to be seriliazed
JSON_obj = {}
# Get meeting ID
page = requests.get(URL)
o = urlparse(URL)
query = parse_qs(o.query)
JSON_obj["meeting_id"] = query["Id"][0]
# Complete HTML File
soup = BeautifulSoup(page.content, "html.parser")
# Most of the page content is found in this container
page_content = soup.find(id="package-container")
###
# MM Header
agenda_header = page_content.find("header", class_="AgendaHeader")
## Header information
# Get the Agenda Header
try:
JSON_obj["agenda_header_subtitle"] = agenda_header.find("p", class_="AgendaHeaderSubTitle").text
except AttributeError:
JSON_obj["agenda_header_subtitle"] = ""
# Get the start time
JSON_obj["start_time"] = agenda_header.find("time").text
# Get the location
try:
JSON_obj["location"] = agenda_header_subtitle = agenda_header.find("div", class_="Value LocationValue").text ### This does not get all location info
except AttributeError:
JSON_obj["location"] = ""
# Get the attendence (seperated by who can and can't vote)
attendance_table = agenda_header.find(class_="AgendaHeaderAttendanceTable").find_all("div")
try:
present = [x.text for x in attendance_table[2].find_all("li")]
except IndexError:
present = []
try:
also_present = [x.text for x in attendance_table[5].find_all("li")]
except IndexError:
also_present = []
JSON_obj["attendance"] = {'present': present, 'also_present': also_present}
###
# MM Body
agenda_items = page_content.find("div", class_="AgendaItems")
## Body information
# Get item containers
agenda_item_containers = agenda_items.find_all("div", class_="AgendaItemContainer indent")
# Get roll call
try:
roll_call = agenda_item_containers[0].find_all("p", class_="Body1")
JSON_obj["roll_call"] = roll_call[2].text.rstrip('.').replace(', and ', ', ').split(', ')
except IndexError:
JSON_obj["roll_call"] = []
if DEBUG:
print(JSON_obj["roll_call"])
# Get generator of item containers
agenda_item_containers = agenda_items.children
item_number = 1
for agenda_item in agenda_item_containers:
# Get titles
titles = [x.text for x in agenda_item.find_all("div", class_="AgendaItemTitle")]
# Get each motion in each item
motions = agenda_item.find_all("ul", class_="AgendaItemMotions")
if DEBUG:
print(item_number)
if motions != None:
item_sub_number = 1
for motion in motions:
# Dictionary to store all motion info
motion_obj = {}
if DEBUG:
print(str(item_number) + '.' + str(item_sub_number))
# Place "anchor"
motion_anchor = [x.parent.parent.parent.parent for x in motion.find_all("div", class_="MotionText RichText")]
# Get motion title
motion_titles = [x.find("div", class_="AgendaItemTitle").text.strip() for x in motion_anchor]
# Get list of who the motion is moved by
moved_by_list = [x.find("span", class_="Value") for x in motion.find_all("div", class_="MovedBy")]
moved_by_list = [x.text for x in moved_by_list]
# Get motion description
motion_description_list = [x.text for x in motion.find_all("div", class_="MotionText RichText")]
# Get motion result
motion_result_list = [x.text for x in motion.find_all("div", class_="MotionResult")]
# Get motion votes
motion_votes_list = [x.text[x.text.find(')') + 1:].split(', and ') for x in motion.find_all("table", class_="MotionVoters")]
# Get motion attachments
motion_attachments_list = [x.find_all("a", class_="Link") for x in motion_anchor]
motion_attachments_list_names = []
motion_attachments_list_links = []
for x in motion_attachments_list:
motion_attachments_list_names.append([y.text for y in x]) # ?
motion_attachments_list_links.append([y['href'] for y in x])
motion_obj["titles"] = motion_titles
motion_obj["moved_by"] = moved_by_list
motion_obj["details"] = motion_description_list
motion_obj["results"] = motion_result_list
motion_obj["votes"] = motion_votes_list
motion_obj['attachment_names'] = motion_attachments_list_names[0]
motion_obj['attachment_links'] = motion_attachments_list_links[0]
motion_obj['attachment_count'] = len(motion_attachments_list_names[0])
# for desc in motion_description_list:
# if len(desc.split()) > s.max_length:
# motion_obj['summary'] = s.summarize(text=desc)[0]
# else:
# motion_obj['summary'] = "Too short to summarize"
if DEBUG:
print(str(item_number) + '.' + str(item_sub_number))
print(motion_titles) # title
print("Moved by: " + str(moved_by_list)) # Moved by
print(motion_description_list) # Other details
print("Result: " + str(motion_result_list)) # Result
print("Votes: " + str(motion_votes_list)) # Votes
print(motion_attachments_list_names[0]) # attachment names
print(motion_attachments_list_links[0]) # attachment links
print()
# Append to JSON object
JSON_obj[f'{item_number}.{item_sub_number}'] = motion_obj
item_sub_number+=1
if DEBUG:
print('-----------------------------------\n\n\n')
item_number+=1
# # Serialize and write to "meeting_minutes.json"
# with open(f"{out_dir}/meeting_minutes.json", "w") as out:
# json.dump(JSON_obj, out, indent=4)
# Add this to data base
return JSON_obj |