File size: 6,194 Bytes
57c4050
a6d7194
 
 
 
57c4050
a6d7194
0fc522e
 
 
57c4050
0fc522e
57c4050
ec13f7a
57c4050
a6d7194
 
 
 
 
 
 
 
 
 
ec13f7a
 
 
a6d7194
 
 
 
5cac51a
71294ad
57c4050
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af6fef8
 
c4bcfe6
57c4050
 
 
 
0253287
57c4050
 
 
 
 
 
 
 
 
 
 
 
 
71294ad
57c4050
 
c4bcfe6
57c4050
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95b49f6
 
 
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
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
from datetime import datetime, timedelta
import uuid
import time
import urllib.request
from lxml import etree
from utils import encode, translate, datemodifier, sentiment_computation, upsert_content

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 = {}
                        print(url)
                        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"))
                            if len(article['originalContent']) < 10:
                                continue
                            CONTENT_ENG = ''
                            for element in article['originalContent'].split("。"):
                                CONTENT_ENG += translate(element) + ' '
                            article['content'] = CONTENT_ENG
                            article['site'] = "State Council"
                            article['originalSite'] = "国务院"
                            article['originalTitle'] = page.xpath("//title/text()")[0]
                            article['title'] = translate(article['originalTitle'])
                            article['url'] = url
                            article['category']= "Policy Release"
                            article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'firstpublishedtime']/@content")[0], "%Y-%m-%d-%H:%M:%S")
                        elif "../../zcfb/" in url:
                            url = url.replace("../../zcfb/", "https://www.ndrc.gov.cn/xxgk/zcfb/")
                            print(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(@class, 'TRS_Editor') or contains(@class, 'article_l')]"))
                            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 Development and Reform Commission"
                            article['originalSite'] = "国家发展和改革委员会"
                            article['originalTitle'] = page.xpath("//meta[@name = 'ArticleTitle']/@content")[0]
                            article['title'] = translate(article['originalTitle'])
                            article['url'] = url
                            article['category']= "Policy Release"
                            article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'PubDate']/@content")[0], "%Y-%m-%d %H:%M:%S")
                        else:
                            url = url.replace("../../", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
                            url = url.replace("./", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
                            print(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(@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 Development and Reform Commission"
                            article['originalSite'] = "国家发展和改革委员会"
                            article['originalTitle'] = page.xpath("//meta[@name = 'ArticleTitle']/@content")[0]
                            article['title'] = translate(article['originalTitle'])
                            article['url'] = url
                            article['category']= "Policy Interpretation"
                            article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'PubDate']/@content")[0], "%Y-%m-%d %H:%M:%S")
                        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)