Init 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 +1,63 @@
+import requests
+import json
+import datetime
+from datetime import datetime as dt
+
+from bs4 import BeautifulSoup
+
+try:
+    from load import config
+except: config = None
+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.bot("link"), headers=headers)
+    page.encoding = 'utf-8'
+
+    soup = BeautifulSoup(page.text, "html.parser")
+
+    # Это в идеале нужно переписать...
+    try: output = table_parser(soup, output); #print(output)
+    except Exception: pass
+    try: output = one_parser(soup, output); #print(output)
+    except Exception: pass
+    try: output = parser_two(soup, output); print(output)
+    except Exception as e: raise(e)
+    #try: output = parser3(soup, output); print(output)
+    #except Exception as e: raise(e)
+    
+
+    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

parser/utils.py

@@ -0,0 +1,68 @@
+
+def table_parser(soup, 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 one_parser(soup, output):
+    raw_data = soup.find("main").findAll("p")
+    date = (
+        raw_data[3].find("span", style="font-size:16px;").b.text.lower()
+        .replace(u"\xa0", u"").replace("на", "").replace("\r", "")
+        .replace("ЗАМІНИ ДО РОЗКЛАДУ".lower(), "").split("\n")
+    )
+    output["date"] = date[1].lstrip(" ")
+
+    for p in raw_data[4].find("span",style="font-size:16px;").b.text.replace(u"\xa0", u"").split("\n"):
+        p = p.lstrip(" ")
+        data_rep = (p.lstrip(" ").split(" ", 1))
+        group = data_rep[0]
+        text = data_rep[1].replace("\r", "").lstrip(" ")
+        output["data"][group] = text
+    return output
+
+def parser_two(soup, output):
+    raw_data = soup.find("main").findAll("p")[2]
+    data = raw_data.text.split("\n")
+    output["date"] = data[1].replace("\r", "")
+
+    for p in data[3:]:
+        r_data = p.split(maxsplit=1)
+        try:
+            group = r_data[0].replace(u"\xa0", u"").replace("\r", "")
+            text = r_data[1].replace(u"\xa0", u"").replace("\r", "")
+        except IndexError: break
+        output["data"][group] = text
+    return output
+
+def parser3(soup, output): 
+    raw_data = soup.find("main").findAll("p")
+
+    output["date"] = (
+        raw_data[2].text
+        .replace("\r", "")
+        .replace("ЗАМІНИ НА", "").lstrip(" ").rstrip(" ").lower()
+    )
+    for p in raw_data[5:]: 
+        r_data = p.text.split("-", maxsplit=1)
+        group = r_data[0]
+        text = r_data[1]
+        output["data"][group] = text
+    return output