File size: 2,824 Bytes
57c4050 |
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 |
import uuid
import time
import urllib.request
from datetime import datetime, timedelta
from lxml import etree
from utils import encode, translate, sentiment_computation, upsert_content
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.stats.gov.cn/sj/sjjd/"
else:
CATEGORY_URL = f"https://www.stats.gov.cn/sj/sjjd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list-content')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = encode(subpage.xpath("//span"))
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[@class='fl pc_1600']/@href")
for url in urls:
try:
article = {}
url = url.replace('./', "https://www.stats.gov.cn/sj/sjjd/", )
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(@class, 'TRS_Editor')]//p"))
if len(article['originalContent']) < 10:
continue
CONTENT_ENG = ''
for element in article['originalContent'].split("。"):
CONTENT_ENG += translate(element) + ' '
article['content'] = CONTENT_ENG
article['site'] = "National Bureau of Statistics"
article['originalSite'] = "国家统计局"
article['originalTitle'] = page.xpath("//title/text()")[0]
article['title'] = translate(article['originalTitle'])
article['url'] = url
article['category']= "Data Interpretation"
article['publishDate'] = date
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['title']+article['publishDate'])
article['sentimentScore'], article['sentimentLabel'] = sentiment_computation(article['content'])
upsert_content(article)
except Exception as error:
print(error) |