commit

ndrc.py

@@ -220,7 +220,7 @@ while i > -1:
                           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 + ' '
+                              content_eng += translator.translate(element, dest='en').text + ' '
                           article['content'] = content_eng
                           article['site'] = "State Council"
                           article['originalSite'] = "国务院"
@@ -229,6 +229,24 @@ while i > -1:
                           article['url'] = url
                           article['category']= "Policy Release"
                           article['publishDate'] = datemodifier_gov(page.xpath("//meta[@name = 'firstpublishedtime']/@content")[0])
+                        elif "/zcfb/tz/" in url:
+                          url = url.replace("../../zcfb/tz/", "https://www.ndrc.gov.cn/xxgk/zcfb/tz/")
+                          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"))
+                          content_eng = ''
+                          for element in article['originalContent'].split("。"):
+                            content_eng += translator.translate(element, dest='en').text + ' '
+                          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'] = translator.translate(article['originalTitle'], dest='en').text
+                          article['url'] = url
+                          article['category']= "Policy Release"
+                          article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'PubDate']/@content")[0])
                         else:
                           url = url.replace("../../", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
                           url = url.replace("./", "https://www.ndrc.gov.cn/xxgk/jd/jd/")