File size: 1,966 Bytes
57c4050 a6d7194 42ba1cc a6d7194 0fc522e 57c4050 0fc522e 57c4050 ec13f7a 57c4050 a6d7194 ec13f7a a6d7194 42ba1cc 57c4050 af6fef8 57c4050 71294ad 57c4050 42ba1cc a6d7194 |
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 |
from datetime import datetime, timedelta
import uuid
import time
import urllib.request
from lxml import etree
from utils import crawl
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.ndrc.gov.cn/xxgk/jd/jd/index.html"
else:
CATEGORY_URL = f"https://www.ndrc.gov.cn/xxgk/jd/jd/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')]/ul/li[not(@class = 'empty')]")
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 = {}
if "www.gov.cn" in url:
article['category']= "Policy Release"
elif "../../zcfb/" in url:
url = url.replace("../../zcfb/", "https://www.ndrc.gov.cn/xxgk/zcfb/")
article['category']= "Policy Release"
else:
url = url.replace("../../", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
url = url.replace("./", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
article['category']= "Policy Interpretation"
crawl(url, article)
except Exception as error:
print(error)
|