first commit

parser/__init__.py

@@ -0,0 +1,2 @@
+from .parser import get_about_replacements, docs_parse
+__all__ = ['get_about_replacements', 'docs_parse']

parser/parser.py

@@ -0,0 +1,67 @@
+import base64
+import json
+import datetime
+from datetime import datetime as dt
+
+import requests
+from bs4 import BeautifulSoup
+
+try:
+    from load import config
+except ImportError: config = None
+try:
+    from .utils import *
+except ImportError: 
+    from utils import *
+
+
+headers = {
+    'user-agent':(
+        "Mozilla/5.0 (Windows NT 10.0; WOW64) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/62.0.3202.9 Safari/537.36"
+    )
+}
+
+
+def date_parser_helper(days:int, parse:str="%d.%m.20%y"):
+    return dt.strftime(
+            dt.now() +
+            datetime.timedelta(days=days),
+            parse
+        )
+
+
+def docs_parse():
+
+    output = {
+        "data":{},
+        "another_teacher":None
+    }
+
+    page = requests.get(config.parser.link, headers=headers)
+    page.encoding = 'utf-8'
+
+    soup = BeautifulSoup(page.text, "lxml")
+
+    # Это в идеале нужно переписать...
+    url = image_parser(soup)
+    with requests.get(url=url, allow_redirects=True, stream=True) as r:
+        output['image'] = True
+        output['date'] = 'невозможно получить!'
+        output['data']['all'] = base64.b64encode(r.content).decode('utf-8')
+
+
+    with open(config.data_file, 'w') as f:
+        json.dump(output, f, ensure_ascii=False)
+        f.close()
+
+
+def get_about_replacements() -> dict:
+    with open(config.data_file, 'r') as f:
+        data = json.loads(f.read())
+        f.close()
+        return data
+
+if __name__ == "__main__":
+    docs_parse()

parser/utils.py

@@ -0,0 +1,34 @@
+from bs4 import BeautifulSoup
+from typing import Any
+
+def table_parser(soup: BeautifulSoup, output):
+    #Date parser
+    date = (soup.find("main").findAll('span', style="color:black"))[1]
+    output["date"] = date.text.replace(u'\xa0', u'')
+
+
+    #Replaces parser
+    replaces = soup.findAll('tr')
+    for data in replaces:
+        
+        text = (
+            data.find("td", valign="top")
+            .find("span", style="color:black")
+            .text.replace(u'\xa0', u'')
+        )
+        group = (
+            data.find("span", style="color:black")
+            .text.replace(" ", "").replace(u'\xa0', u''))
+        output["data"][group] = text
+    
+    return output
+
+
+def image_parser(soup: BeautifulSoup):
+    image: Any
+    extension = ('png', 'jpg')
+    main = soup.find("main")
+    for ext in extension:
+        image = main.select(f'img[src$=".{ext}"]')
+        if image:
+            return image[0]['src']