| 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.gov.cn/zhengce/jiedu/home.htm" | |
| else: | |
| CATEGORY_URL = f"https://www.gov.cn/zhengce/jiedu/home_{i}.htm" | |
| 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, 'news_box')]//h4") | |
| 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 = {} | |
| url = url.replace('../', 'https://www.gov.cn/zhengce/') | |
| 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("γ"): | |
| CONTENT_ENG += translate(element) + ' ' | |
| article['content'] = CONTENT_ENG | |
| article['site'] = "State Council" | |
| article['originalSite'] = "ε½ε‘ι’" | |
| article['originalTitle'] = page.xpath("//title/text()")[0] | |
| article['title'] = translate(article['originalTitle']) | |
| article['url'] = url | |
| article['category']= "Policy Interpretation" | |
| article['publishDate'] = datemodifier(page.xpath("//meta[@name = 'firstpublishedtime']/@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) | |
| i = 0 | |
| while i > -1: | |
| if i == 0: | |
| CATEGORY_URL = "https://www.gov.cn/zhengce/zuixin/home.htm" | |
| else: | |
| CATEGORY_URL = f"https://www.gov.cn/zhengce/zuixin/home_{i}.htm" | |
| 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, 'news_box')]//h4") | |
| 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 = {} | |
| url = url.replace('../', 'https://www.gov.cn/zhengce/') | |
| 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("γ"): | |
| CONTENT_ENG += translate(article['originalContent']) + ' ' | |
| article['content'] = CONTENT_ENG | |
| article['site'] = "State Council" | |
| article['originalSite'] = "ε½ε‘ι’" | |
| 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") | |
| 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) | |