File size: 11,742 Bytes
0fc522e b05adb3 0fc522e ec13f7a 0fc522e b348cfd 0fc522e b348cfd 0fc522e ec13f7a 0fc522e ec13f7a 0fc522e b348cfd |
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 |
import requests
from datetime import datetime, timedelta
from decimal import Decimal
import boto3
import uuid
import time
import urllib.request
from lxml import etree
from googletrans import Translator
from transformers import pipeline
from PyPDF2 import PdfReader
import os
AWS_ACCESS_KEY_ID = os.environ['AWS_ACCESS_KEY_ID']
AWS_SECRET_ACCESS_KEY = os.environ['AWS_SECRET_ACCESS_KEY']
analyzer = pipeline("sentiment-analysis", model="ProsusAI/finbert")
translator = Translator()
def datemodifier(date_string):
"""Date Modifier Function"""
try:
to_date = time.strptime(date_string,"%Y-%m-%d-%H:%M:%S")
return time.strftime("%Y-%m-%d",to_date)
except:
return False
def fetch_url(url):
response = requests.get(url)
if response.status_code == 200:
return response.text
else:
return None
def translist(infolist):
"""Translist Function"""
out = list(filter(lambda s: s and
(isinstance (s,str) or len(s.strip()) > 0), [i.strip() for i in infolist]))
return out
def encode(content):
"""Encode Function"""
text = ''
for element in content[:1]:
if isinstance(element, etree._Element):
subelement = etree.tostring(element).decode()
subpage = etree.HTML(subelement)
tree = subpage.xpath('//text()')
line = ''.join(translist(tree)).\
replace('\n','').replace('\t','').replace('\r','').replace(' ','').strip()
else:
line = element
text += line
index = text.find('打印本页')
if index != -1:
text = text[:index]
return text
def extract_from_pdf(url):
# Send a GET request to the URL and retrieve the PDF content
response = requests.get(url)
pdf_content = response.content
# Save the PDF content to a local file
with open("downloaded_file.pdf", "wb") as f:
f.write(pdf_content)
# Open the downloaded PDF file and extract the text
with open("downloaded_file.pdf", "rb") as f:
pdf_reader = PdfReader(f)
num_pages = len(pdf_reader.pages)
extracted_text = ""
extracted_text_eng = ""
for page in range(num_pages):
text = pdf_reader.pages[page].extract_text()
if text and text[0].isdigit():
text = text[1:]
first_newline_index = text.find('\n')
text = text[:first_newline_index+1].replace('\n', ' ') + text[first_newline_index+1:].replace('\n', '')
extracted_text_eng += translator.translate(text, dest='en').text
extracted_text += text
return extracted_text, extracted_text_eng
def get_db_connection():
"""Get dynamoDB connection"""
dynamodb = boto3.resource(
service_name='dynamodb',
region_name='us-east-1',
aws_access_key_id=AWS_ACCESS_KEY_ID,
aws_secret_access_key=AWS_SECRET_ACCESS_KEY
)
return dynamodb
def upsert_content(report):
"""Upsert the content records"""
dynamodb = get_db_connection()
table = dynamodb.Table('article_china')
# Define the item data
item = {
'id': str(report['id']),
'site': report['site'],
'title': report['title'],
# 'originalSite': report['originalSite'],
# 'originalTitle': report['originalTitle'],
# 'originalContent': report['originalContent'],
'category': report['category'],
# 'author': report['author'],
'content': report['content'],
'publishDate': report['publishDate'],
'link': report['url'],
# 'attachment': report['reporturl'],
# 'authorID': str(report['authorid']),
'sentimentScore': str(Decimal(report['sentimentScore']).quantize(Decimal('0.01'))),
'sentimentLabel': report['sentimentLabel'],
'LastModifiedDate': datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
}
response = table.put_item(Item=item)
print(response)
i = 0
while i > -1:
if i == 0:
categoryu_url = "https://www.gov.cn/zhengce/jiedu/home.htm"
else:
categoryu_url = f"https://www.gov.cn/zhengce/jiedu/home_{i}.htm"
i = i + 1
req = urllib.request.urlopen(categoryu_url)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'news_box')]//h4")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=183)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace('../', 'https://www.gov.cn/zhengce/')
if "https://www.gov.cn" in url:
req = urllib.request.urlopen(url)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
article['originalContent'] = encode(page.xpath("//div[contains(@id, 'UCAP-CONTENT')]//p"))
content_eng = ''
for element in article['originalContent'].split("。"):
content_eng += translator.translate(element, dest='en').text + ' '
article['content'] = content_eng
article['site'] = "State Council"
article['originalSite'] = "国务院"
article['originalTitle'] = page.xpath("//title/text()")[0]
article['title'] = translator.translate(article['originalTitle'], dest='en').text
article['url'] = url
article['category']= "Policy Interpretation"
article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'firstpublishedtime']/@content")[0])
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['title']+article['publishDate'])
label_dict = {
"positive": "+",
"negative": "-",
"neutral": "0",
}
sentiment_score = 0
maximum_value = 0
raw_sentiment = analyzer(article['content'][:512], return_all_scores=True)
sentiment_label = None
for sentiment_dict in raw_sentiment[0]:
value = sentiment_dict["score"]
if value > maximum_value:
sentiment_label = sentiment_dict["label"]
maximum_value = value
if sentiment_dict["label"] == "positive":
sentiment_score = sentiment_score + value
if sentiment_dict["label"] == "negative":
sentiment_score = sentiment_score - value
else:
sentiment_score = sentiment_score + 0
article['sentimentScore'] = sentiment_score
article['sentimentLabel'] = label_dict[sentiment_label]
upsert_content(article)
except Exception as error:
print(error)
i = 0
while i > -1:
if i == 0:
categoryu_url = "https://www.gov.cn/zhengce/zuixin/home.htm"
else:
categoryu_url = f"https://www.gov.cn/zhengce/zuixin/home_{i}.htm"
i = i + 1
req = urllib.request.urlopen(categoryu_url)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'news_box')]//h4")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=183)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace('../', 'https://www.gov.cn/zhengce/')
if "https://www.gov.cn" in url:
req = urllib.request.urlopen(url)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
article['originalContent'] = encode(page.xpath("//div[contains(@id, 'UCAP-CONTENT')]//p"))
content_eng = ''
for element in article['originalContent'].split("。"):
content_eng += translator.translate(element, dest='en').text + ' '
article['content'] = content_eng
article['site'] = "State Council"
article['originalSite'] = "国务院"
article['originalTitle'] = page.xpath("//title/text()")[0]
article['title'] = translator.translate(article['originalTitle'], dest='en').text
article['url'] = url
article['category']= "Policy Release"
article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'firstpublishedtime']/@content")[0])
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['title']+article['publishDate'])
label_dict = {
"positive": "+",
"negative": "-",
"neutral": "0",
}
sentiment_score = 0
maximum_value = 0
raw_sentiment = analyzer(article['content'][:512], return_all_scores=True)
sentiment_label = None
for sentiment_dict in raw_sentiment[0]:
value = sentiment_dict["score"]
if value > maximum_value:
sentiment_label = sentiment_dict["label"]
maximum_value = value
if sentiment_dict["label"] == "positive":
sentiment_score = sentiment_score + value
if sentiment_dict["label"] == "negative":
sentiment_score = sentiment_score - value
else:
sentiment_score = sentiment_score + 0
article['sentimentScore'] = sentiment_score
article['sentimentLabel'] = label_dict[sentiment_label]
upsert_content(article)
except Exception as error:
print(error)
|