File size: 1,794 Bytes
57c4050
 
 
 
42ba1cc
57c4050
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42ba1cc
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
import time
import urllib.request
from datetime import datetime, timedelta
from lxml import etree
from utils import crawl

categories = ['jdzhsw','jdgnmy','jddwmy','jdtzhz']
for category in categories:
    i = 1
    while i > -1:
        if i == 1:
            URL = f"http://www.mofcom.gov.cn/article/zcjd/{category}/"
        else:
            URL = f"http://www.mofcom.gov.cn/article/zcjd/{category}/?{i}"
        i = i + 1
        req = urllib.request.urlopen(URL)
        text = req.read()
        html_text = text.decode("utf-8")
        page = etree.HTML(html_text)
        articlelist = page.xpath("//section[contains(@class, 'listCon iListCon f-mt30')]/ul/li")
        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 %H:%M:%S")), "%Y-%m-%d")
                if  parsed_datetime < (datetime.today() - timedelta(days=183)):
                    i = -1
                else:
                    urls = subpage.xpath("//a/@href")
                    for url in urls:
                        try:
                            article = {}
                            if '/article/zcjd' in url:
                                url = "http://www.mofcom.gov.cn" + url
                                article['category']= "Policy Interpretation"
                            else:
                                article['category']= "Policy Release"
                            crawl(url, article)
                        except Exception as error:
                            print(error)