From 83e2d5efb5a3941249d42a012f603319c94f7b5d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=98=D0=BB=D1=8C=D1=8F?= <Lutiyroker@yandex.ru>
Date: Fri, 30 Apr 2021 18:40:09 +0300
Subject: [PATCH] add homework3

---
 database/__init__.py |   0
 database/database.py |  42 ++++++++++++++
 database/mixins.py   |   9 +++
 database/models.py   |  52 +++++++++++++++++
 gb_blog_parse.py     | 131 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 234 insertions(+)
 create mode 100644 database/__init__.py
 create mode 100644 database/database.py
 create mode 100644 database/mixins.py
 create mode 100644 database/models.py
 create mode 100644 gb_blog_parse.py

diff --git a/database/__init__.py b/database/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/database/database.py b/database/database.py
new file mode 100644
index 0000000..f25596c
--- /dev/null
+++ b/database/database.py
@@ -0,0 +1,42 @@
+import sqlalchemy.exc
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+from . import models
+
+
+class Database:
+    def __init__(self, db_url):
+        self.engine = create_engine(db_url)
+        models.Base.metadata.create_all(bind=self.engine)
+        self.maker = sessionmaker(bind=self.engine)
+
+    def get_or_create(self, session, model, **kwargs):
+        instance = session.query(model).filter_by(**kwargs).first()
+        if instance:
+            return instance
+        else:
+            instance = model(**kwargs)
+            return instance
+
+    def add_post(self, data):
+        session = self.maker()
+        post = models.Post(
+            **data["post_data"],
+            author=self.get_or_create(session, models.Author, **data["author_data"]),
+            tags=[self.get_or_create(session, models.Tag, **tag_params) for tag_params in data["tags_data"]],
+            comments=[models.Comment(**comment_params) for comment_params in data["comments_data"]]
+        )
+        for itm in post.tags:
+            itm.posts.append(post)
+        for itm in post.comments:
+            if itm.parent_id:
+                itm.parent = session.query(models.Comment).filter_by(id=itm.parent_id).first()
+
+        try:
+            session.add(post)
+            session.commit()
+        except sqlalchemy.exc.IntegrityError:
+            session.rollback()
+        finally:
+            session.close()
diff --git a/database/mixins.py b/database/mixins.py
new file mode 100644
index 0000000..b0a7f50
--- /dev/null
+++ b/database/mixins.py
@@ -0,0 +1,9 @@
+from sqlalchemy import Column, Integer, String
+
+
+class IdMixin:
+    id = Column(Integer, primary_key=True, autoincrement=True)
+
+
+class UrlMixin:
+    url = Column(String, unique=True, nullable=False)
\ No newline at end of file
diff --git a/database/models.py b/database/models.py
new file mode 100644
index 0000000..dc84c60
--- /dev/null
+++ b/database/models.py
@@ -0,0 +1,52 @@
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy.orm import relationship
+
+from sqlalchemy import Column, Integer, String, ForeignKey, Text, Table, DateTime
+
+from .mixins import UrlMixin
+
+
+Base = declarative_base()
+
+tag_post = Table(
+    "tag_post",
+    Base.metadata,
+    Column("post_id", Integer, ForeignKey("post.id")),
+    Column("tag_id", Integer, ForeignKey("tag.id")),
+)
+
+
+class Post(Base, UrlMixin):
+    __tablename__ = "post"
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    title = Column(String(250), nullable=False, unique=False)
+    img_url = Column(String, unique=False, nullable=True)
+    date_published = Column(DateTime, unique=False, nullable=True)
+    author_id = Column(Integer, ForeignKey("author.id"), nullable=True)
+    author = relationship("Author", backref="posts")
+    tags = relationship("Tag", secondary=tag_post)
+
+
+class Author(Base, UrlMixin):
+    __tablename__ = "author"
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    name = Column(String(150), nullable=False)
+
+
+class Tag(Base, UrlMixin):
+    __tablename__ = "tag"
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    name = Column(String(150), nullable=False)
+    posts = relationship(Post, secondary=tag_post)
+
+
+class Comment(Base):
+    __tablename__ = "comment"
+    id = Column(Integer, primary_key=True, autoincrement=True)
+    body = Column(Text, nullable=False, unique=False)
+    created_at = Column(DateTime, unique=False, nullable=True)
+    author_of_comment = Column(String(150), nullable=False)
+    post_id = Column(Integer, ForeignKey("post.id"), nullable=False)
+    parent_id = Column(Integer, ForeignKey("comment.id"), nullable=True)
+    post = relationship(Post, backref="comments")
+    parent = relationship("Comment", uselist=False, post_update=True)
diff --git a/gb_blog_parse.py b/gb_blog_parse.py
new file mode 100644
index 0000000..9eb840c
--- /dev/null
+++ b/gb_blog_parse.py
@@ -0,0 +1,131 @@
+import time
+import typing
+import datetime
+import requests
+from urllib.parse import urljoin
+import bs4
+
+from database.database import Database
+
+
+class GbBlogParse:
+    def __init__(self, start_url, db):
+        self.time = time.time()
+        self.start_url = start_url
+        self.db = db
+        self.done_urls = set()
+        self.tasks = []
+        start_task = self.get_task(self.start_url, self.parse_feed)
+        self.tasks.append(start_task)
+        self.done_urls.add(self.start_url)
+
+    def _get_response(self, url, *args, **kwargs):
+        if self.time + 0.9 < time.time():
+            time.sleep(0.5)
+        response = requests.get(url, *args, **kwargs)
+        self.time = time.time()
+        print(url)
+        return response
+
+    def _get_soup(self, url, *args, **kwargs):
+        soup = bs4.BeautifulSoup(self._get_response(url, *args, **kwargs).text, "lxml")
+        return soup
+
+    def get_task(self, url: str, callback: typing.Callable) -> typing.Callable:
+        def task():
+            soup = self._get_soup(url)
+            return callback(url, soup)
+
+        if url in self.done_urls:
+            return lambda *_, **__: None
+        self.done_urls.add(url)
+        return task
+
+    def task_creator(self, url, tags_list, callback):
+        links = set(
+            urljoin(url, itm.attrs.get("href")) for itm in tags_list if itm.attrs.get("href")
+        )
+        for link in links:
+            task = self.get_task(link, callback)
+            self.tasks.append(task)
+
+    def parse_feed(self, url, soup):
+        ul_pagination = soup.find("ul", attrs={"class": "gb__pagination"})
+        self.task_creator(url, ul_pagination.find_all("a"), self.parse_feed)
+        post_wrapper = soup.find("div", attrs={"class": "post-items-wrapper"})
+        self.task_creator(
+            url, post_wrapper.find_all("a", attrs={"class": "post-item__title"}), self.parse_post
+        )
+
+    def parse_post(self, url, soup):
+        author_tag = soup.find("div", attrs={"itemprop": "author"})
+
+        first_img = soup.find("div", attrs={"class": "blogpost-content"}).find("img")
+        if first_img:  # Попались статьи без картинок
+            first_img_link = first_img.attrs.get("src")
+        else:
+            first_img_link = None
+
+        date_published = soup.find("div", attrs={"class": "blogpost-date-views"}).find("time").attrs.get("datetime")
+        date_obj = datetime.datetime.strptime(date_published, '%Y-%m-%dT%H:%M:%S%z')
+
+        data = {
+            "post_data": {
+                "title": soup.find("h1", attrs={"class": "blogpost-title"}).text,
+                "url": url,
+                "id": soup.find("comments").attrs.get("commentable-id"),
+                "img_url": first_img_link,
+                "date_published": date_obj,
+            },
+            "author_data": {
+                "url": urljoin(url, author_tag.parent.attrs.get("href")),
+                "name": author_tag.text,
+            },
+            "tags_data": [
+                {"name": tag.text, "url": urljoin(url, tag.attrs.get("href"))}
+                for tag in soup.find_all("a", attrs={"class": "small"})
+            ],
+            "comments_data": self._get_comments(soup.find("comments").attrs.get("commentable-id")),
+        }
+        return data
+
+    def _get_comments(self, post_id):
+        api_path = f"/api/v2/comments?commentable_type=Post&commentable_id={post_id}&order=desc"
+        response = self._get_response(urljoin(self.start_url, api_path))
+        data = response.json()
+        data = self._restructure_comments(data, post_id)
+        return data
+
+    def _restructure_comments(self, data, post_id):
+        comment_keys = ('id', 'parent_id', 'body', 'created_at')
+        result = []
+        for itm in data:
+            tmp_dict = {}
+            for param in comment_keys:
+                tmp_dict.update({param: itm["comment"][param]})
+            tmp_dict.update({"post_id": post_id})
+            tmp_dict.update({"author_of_comment": itm["comment"]["user"]['full_name']})
+            # Убрал миллисекунды из 'created_at', формат '%Y-%m-%dT%H:%M:%S.%f%z' выдавал ошибку
+            tmp_dict['created_at'] = tmp_dict['created_at'][:19] + tmp_dict['created_at'][23:]
+            tmp_dict['created_at'] = datetime.datetime.strptime(tmp_dict['created_at'], '%Y-%m-%dT%H:%M:%S%z')
+            result.append(tmp_dict)
+            if itm["comment"]["children"]:
+                for child in self._restructure_comments(itm["comment"]["children"], post_id):
+                    result.append(child)
+        return result
+
+    def run(self):
+        for task in self.tasks:
+            task_result = task()
+            if isinstance(task_result, dict):
+                self.save(task_result)
+
+    def save(self, data):
+        self.db.add_post(data)
+
+
+if __name__ == "__main__":
+    # collection = MongoClient()["gb_parse_20_04"]["gb_blog"]
+    db = Database("sqlite:///gb_blog.db")
+    parser = GbBlogParse("https://gb.ru/posts", db)
+    parser.run()