hfr-api 0.0.2__tar.gz

hfr_api-0.0.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 dotvav
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

hfr_api-0.0.2/PKG-INFO

@@ -0,0 +1,27 @@
+Metadata-Version: 2.2
+Name: hfr_api
+Version: 0.0.2
+Summary: A Python library to interface with forum.hardware.fr
+Home-page: https://gitea.ruk.info/roukine/hfr
+Author: MycRub
+Author-email: mycrub@mycrub.net
+License: MIT
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests==2.32.3
+Requires-Dist: beautifulsoup4==4.12.3
+Requires-Dist: sortedcontainers==2.4.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# HFR
+
+A python library to interface with forum.hardware.fr

hfr_api-0.0.2/README.md

@@ -0,0 +1,3 @@
+# HFR
+
+A python library to interface with forum.hardware.fr

hfr_api-0.0.2/hfr/__init__.py

@@ -0,0 +1,5 @@
+"""hfr_api: A Python library to interface with forum.hardware.fr"""
+
+from . import bb
+from .message import Message
+from .topic import Topic

hfr_api-0.0.2/hfr/bb.py

@@ -0,0 +1,118 @@
+"""BB code handling"""
+
+from bs4 import BeautifulSoup, NavigableString
+
+
+def convert_inline_tags(html: str, context: dict = {}) -> str:
+    soup = BeautifulSoup(html, "html.parser")
+
+    for element in soup.find_all(True, recursive=False):
+        if element.name == "strong":
+            element.replace_with(
+                NavigableString(
+                    f"[b]{convert_inline_tags(element.decode_contents(), context)}[/b]"
+                )
+            )
+        elif element.name == "span" and "u" in element.get("class", []):
+            element.replace_with(
+                NavigableString(
+                    f"[u]{convert_inline_tags(element.decode_contents(), context)}[/u]"
+                )
+            )
+        elif element.name == "span" and element.get("style"):
+            style = element.get("style")
+            if len(style) > 7 and style[:7] == "color:#":
+                color = style[-6:]
+                element.replace_with(
+                    NavigableString(
+                        f"[#{color}]{convert_inline_tags(element.decode_contents(), context)}[/#{color}]"
+                    )
+                )
+        elif element.name == "em":
+            element.replace_with(
+                NavigableString(
+                    f"[i]{convert_inline_tags(element.decode_contents(), context)}[/i]"
+                )
+            )
+        elif element.name == "strike":
+            element.replace_with(
+                NavigableString(
+                    f"[strike]{convert_inline_tags(element.decode_contents(), context)}[/strike]"
+                )
+            )
+        elif element.name in ("ul", "ol"):
+            context["not_first_line"] = False
+            element.replace_with(
+                NavigableString(
+                    f"{convert_inline_tags(element.decode_contents(), context)}"
+                )
+            )
+            context["not_first_line"] = True
+        elif element.name == "li":
+            table_class = context.get("table_class", "")
+            bullet_style = "" if table_class == "code" else "[*]"
+            new_line = "\n" if context.get("not_first_line", False) else ""
+            context["not_first_line"] = True
+            element.replace_with(
+                NavigableString(
+                    f"{new_line}{bullet_style}{convert_inline_tags(element.decode_contents(), context)}"
+                )
+            )
+        elif element.name == "a":
+            href = element.get("href", "")
+            if len(href) > 6 and href[:7] == "mailto:":
+                element.replace_with(NavigableString(f"[email]{href[7:]}[/email]"))
+            else:
+                element.replace_with(
+                    NavigableString(
+                        f"[url={href}]{convert_inline_tags(element.decode_contents(), context)}[/url]"
+                    )
+                )
+        elif element.name == "img":
+            src = element.get("src", "")
+            alt = element.get("alt", "")
+            if alt[0] in ("[", ":"):
+                # For smileys, just use the alt text
+                element.replace_with(NavigableString(alt))
+            else:
+                # For regular images, convert to BB code format
+                element.replace_with(NavigableString(f"[img]{src}[/img]"))
+        elif element.name == "table":
+            table_class = element.get("class")[0] if element.get("class") else ""
+            new_context = {"table_class": table_class}
+            if "citation" in table_class:
+                bb_tag = "quotemsg"
+                href = element.find("a").get("href")
+                bb_details = f"={href.split('#t')[1]},0,0"  # TODO create reference =msgid,?,userid
+            else:
+                bb_tag = table_class
+                bb_details = ""
+            content = element.find(["p", "ol"])
+            if content:
+                converted_content = convert_inline_tags(
+                    content.decode_contents(), new_context
+                )
+                if len(converted_content) and converted_content[-1] == "\n":
+                    converted_content = converted_content[
+                        :-1
+                    ]  # remove stupid trailing "\n"
+                element.replace_with(
+                    NavigableString(
+                        f"[{bb_tag}{bb_details}]{converted_content}[/{bb_tag}]"
+                    )
+                )
+        else:
+            if not isinstance(element, NavigableString):
+                element.replace_with(
+                    NavigableString(
+                        convert_inline_tags(element.decode_contents(), context)
+                    )
+                )
+
+    return soup.get_text()
+
+
+def html_to_bb(html: str) -> str:
+    return convert_inline_tags(
+        html.replace("&nbsp;", "").replace("\n", "").replace("<br />", "\n")
+    ).strip()

hfr_api-0.0.2/hfr/message.py

@@ -0,0 +1,67 @@
+"""An HFR message"""
+
+from datetime import datetime
+from typing import TYPE_CHECKING
+
+from bs4 import NavigableString
+
+from . import bb
+
+if TYPE_CHECKING:
+    from .topic import Topic
+
+
+class Message:
+    def __init__(
+        self, topic, id: int, posted_at: datetime, author: str, text: str
+    ) -> None:
+        self.topic = topic
+        self.id = id
+        self.posted_at = posted_at
+        self.author = author
+        self.text = text
+
+    @classmethod
+    def from_html(cls, topic: "Topic", html: NavigableString):
+        case1 = html.find("td", class_="messCase1")
+
+        author = case1.find("b", class_="s2").string.replace("\u200b", "")
+        if author == "Publicité":
+            return None
+
+        id = case1.find("a", rel="nofollow").attrs["href"][2:]
+
+        case2 = html.find("td", class_="messCase2")
+        posted_at_str = (
+            case2.find("div", class_="toolbar").find("div", class_="left").string
+        )
+        posted_at = Message.parse_timestamp(posted_at_str)
+
+        text_tag = case2.find("div", id=f"para{id}")
+        text = bb.html_to_bb(text_tag.decode_contents())
+
+        return cls(topic, id, posted_at, author, text)
+
+    @staticmethod
+    def parse_timestamp(timestamp_str: str) -> datetime:
+        d = timestamp_str[9:19]
+        t = timestamp_str[22:30]
+        return datetime.strptime(f"{d} {t}", "%d-%m-%Y %H:%M:%S")
+
+    def to_dict(self) -> dict:
+        return {
+            "id": self.id,
+            "author": self.author,
+            "posted_at": str(self.posted_at),
+            "text": self.text,
+        }
+
+    @classmethod
+    def from_dict(cls, topic, data: dict):
+        return cls(
+            topic,
+            data["id"],
+            datetime.fromtimestamp(int(data["posted_at"])),
+            data["author"],
+            data["text"],
+        )

hfr_api-0.0.2/hfr/topic.py

@@ -0,0 +1,147 @@
+"""An HFR Topic"""
+
+import logging
+import time
+from datetime import date, datetime
+
+import requests
+from bs4 import BeautifulSoup
+from sortedcontainers import SortedDict
+
+from .message import Message
+
+logger = logging.getLogger()
+
+
+def date_to_str(some_date: str | date | datetime) -> str:
+    if isinstance(some_date, datetime):
+        return str(some_date.date())
+    elif isinstance(some_date, date):
+        return str(some_date)
+    elif isinstance(some_date, str):
+        return some_date
+    return None
+
+
+class Topic:
+    def __init__(
+        self,
+        cat: int,
+        subcat: int,
+        post: int,
+        title: str = "",
+        max_page: int = 0,
+        max_date: str = "1970-01-01",
+    ) -> None:
+        self.cat = cat
+        self.subcat = subcat
+        self.post = post
+        self.title = title
+        self.max_page = max_page
+        self.max_date = max_date
+        self.messages = dict()
+
+    @property
+    def id(self) -> str:
+        return f"{self.cat}#{self.subcat}#{self.post}"
+
+    def parse_page_html(self, html: str) -> dict:
+        soup = BeautifulSoup(html, "html.parser")
+        self.title = soup.find("h3").text
+
+        # Find highest page number
+        pages_block = soup.find("tr", class_="fondForum2PagesHaut")
+        page_links = pages_block.find_all("a", class_="cHeader")
+
+        if self.max_page == 0:
+            max_page = 1
+            for page in page_links:
+                href = page.attrs["href"]
+                for param in href.split("&"):
+                    kv = param.split("=")
+                    if kv[0] == "page":
+                        if int(kv[1]) > max_page:
+                            max_page = int(kv[1])
+                        break
+            self.max_page = max_page
+
+        ts_min = 0
+        ts_max = 0
+
+        # Find all messages in the page
+        messages_soup = soup.find_all("table", class_="messagetable")
+        for message_block in messages_soup:
+            message = Message.from_html(self, message_block)
+            if message:
+                self.add_message(message)
+                if ts_min == 0 or ts_min > message.posted_at:
+                    ts_min = message.posted_at
+                if ts_max == 0 or ts_max < message.posted_at:
+                    ts_max = message.posted_at
+
+        return {"ts_min": ts_min, "ts_max": ts_max}
+
+    def add_message(self, message) -> None:
+        msg_date = date_to_str(message.posted_at)
+
+        if msg_date in self.messages:
+            messages_for_date = self.messages[msg_date]
+        else:
+            if msg_date > self.max_date:
+                self.max_date = msg_date
+            logger.debug(f"Got a message at date {msg_date}")
+            messages_for_date = SortedDict()
+            self.messages[msg_date] = messages_for_date
+        messages_for_date[message.id] = message
+
+    def load_page(self, page: int) -> dict:
+        time.sleep(1)
+
+        url = f"https://forum.hardware.fr/forum2.php?config=hfr.inc&cat={self.cat}&subcat={self.subcat}&post={self.post}&print=1&page={page}"
+
+        r = requests.get(
+            url,
+            headers={
+                "Accept": "text/html",
+                "Accept-Encoding": "gzip, deflate, br, zstd",
+                "User-Agent": "HFRTopicSummarizer",
+            },
+        )
+        html = r.text
+
+        return self.parse_page_html(html)
+
+    def has_date(self, msg_date: str | date | datetime) -> bool:
+        return date_to_str(msg_date) in self.messages.keys()
+
+    def messages_on_date(self, msg_date: str):
+        date_str = str(msg_date)
+        if date_str in self.messages:
+            return self.messages[date_str].values()
+        else:
+            return ()
+
+    def to_dict(self) -> dict:
+        return {
+            "topic_id": f"{self.cat}#{self.subcat}#{self.post}",
+            "title": self.title,
+            "max_page": self.max_page,
+            "max_date": self.max_date,
+        }
+
+    @classmethod
+    def from_dict(cls, data: dict):
+        if "topic_id" in data:
+            (cat, subcat, post) = str.split(data["topic_id"], "#")
+            return cls(
+                cat, subcat, post, data["title"], data["max_page"], data["max_date"]
+            )
+        else:
+            return cls(
+                data["cat"],
+                data["subcat"],
+                data["post"],
+                data["title"],
+                data["max_page"],
+                data["max_date"],
+            )

hfr_api-0.0.2/hfr_api.egg-info/PKG-INFO

@@ -0,0 +1,27 @@
+Metadata-Version: 2.2
+Name: hfr_api
+Version: 0.0.2
+Summary: A Python library to interface with forum.hardware.fr
+Home-page: https://gitea.ruk.info/roukine/hfr
+Author: MycRub
+Author-email: mycrub@mycrub.net
+License: MIT
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests==2.32.3
+Requires-Dist: beautifulsoup4==4.12.3
+Requires-Dist: sortedcontainers==2.4.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# HFR
+
+A python library to interface with forum.hardware.fr

hfr_api-0.0.2/hfr_api.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+hfr/__init__.py
+hfr/bb.py
+hfr/message.py
+hfr/topic.py
+hfr_api.egg-info/PKG-INFO
+hfr_api.egg-info/SOURCES.txt
+hfr_api.egg-info/dependency_links.txt
+hfr_api.egg-info/requires.txt
+hfr_api.egg-info/top_level.txt
+tests/test_bb.py

hfr_api-0.0.2/hfr_api.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

hfr_api-0.0.2/hfr_api.egg-info/requires.txt

@@ -0,0 +1,3 @@
+requests==2.32.3
+beautifulsoup4==4.12.3
+sortedcontainers==2.4.0

hfr_api-0.0.2/hfr_api.egg-info/top_level.txt

@@ -0,0 +1 @@
+hfr

hfr_api-0.0.2/pyproject.toml

@@ -0,0 +1,2 @@
+[tool.pytest.ini_options]
+asyncio_mode = "auto"

hfr_api-0.0.2/setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+description-file = README.md
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

hfr_api-0.0.2/setup.py

@@ -0,0 +1,20 @@
+import setuptools
+
+with open("README.md", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="hfr_api",
+    version="0.0.2",
+    author="MycRub",
+    author_email="mycrub@mycrub.net",
+    description="A Python library to interface with forum.hardware.fr",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    license="MIT",
+    url="https://gitea.ruk.info/roukine/hfr",
+    packages=setuptools.find_packages(exclude=("tests", "tests.*")),
+    install_requires=["requests==2.32.3","beautifulsoup4==4.12.3","sortedcontainers==2.4.0"],
+    python_requires=">=3.13",
+    include_package_data=True,
+)

hfr_api-0.0.2/tests/test_bb.py

@@ -0,0 +1,64 @@
+from hfr import bb
+
+def test_html_to_bb_basic():
+    assert bb.html_to_bb("<strong>x</strong>") == "[b]x[/b]"
+    assert bb.html_to_bb("<em>x</em>") == "[i]x[/i]"
+    assert bb.html_to_bb("<span class=\"u\">x</span>") == "[u]x[/u]"
+    assert bb.html_to_bb("<strike>x</strike>") == "[strike]x[/strike]"
+    assert bb.html_to_bb("<a href=\"x\">y</a>") == "[url=x]y[/url]"
+    assert bb.html_to_bb("<img src=\"x\" alt=\"y\"/>") == "[img]x[/img]"
+    assert bb.html_to_bb("<img src=\"x\" alt=\":o\"/>") == ":o"
+    assert bb.html_to_bb("<img src=\"x\" alt=\"[:y]\"/>") == "[:y]"
+    assert bb.html_to_bb("<ul><li> x</li></ul>") == "[*] x"
+    assert bb.html_to_bb("<a href=\"mailto:lolcat@lol.cat\">") == "[email]lolcat@lol.cat[/email]"
+
+
+def test_html_to_bb_advanced():
+    input = """<p>Un test avec du <strong>gras et de <em>l'italique</em> dans le gras</strong>. Du <span class="u">souligné</span> et du <strike>barré</strike>. Aussi, un smiley perso <img src="https://forum-images.hardware.fr/images/perso/mycrub.gif" alt="[:mycrub]" title="[:mycrub]" /> et un smiley de base <img src="https://forum-images.hardware.fr/icones/redface.gif" alt=":o" title=":o" /> ainsi que
+<br /></p><ul><li> une image <img src="https://forum-images.hardware.fr/images/perso/1/mycrub.gif" alt="https://forum-images.hardware.fr/images/perso/1/mycrub.gif" title="https://forum-images.hardware.fr/images/perso/1/mycrub.gif" onload="md_verif_size(this,'Cliquez pour agrandir','2','250')" style="margin: 5px"/>
+</li><li> <a rel="nofollow" href="https://lolcat.lol.cat" target="_blank" class="cLink">un lien</a></li></ul><p><div style="clear: both;"> </div></p></div>"""
+    expected = """Un test avec du [b]gras et de [i]l'italique[/i] dans le gras[/b]. Du [u]souligné[/u] et du [strike]barré[/strike]. Aussi, un smiley perso [:mycrub] et un smiley de base :o ainsi que
+[*] une image [img]https://forum-images.hardware.fr/images/perso/1/mycrub.gif[/img]
+[*] [url=https://lolcat.lol.cat]un lien[/url]"""
+    output = bb.html_to_bb(input)
+    assert expected == output
+
+    input = """<div id="para1980038934"><p>Un quote qui contient du souligné:
+<br /></p><div class="container"><table class="citation"><tr class="none"><td><b class="s1"><a href="/forum2.php?config=hfr.inc&amp;cat=prive&amp;post=3042031&amp;page=1&amp;p=1&amp;sondage=0&amp;owntopic=0&amp;trash=0&amp;trash_post=0&amp;print=0&amp;numreponse=0&amp;quote_only=0&amp;new=0&amp;nojs=0#t1980038387" class="Topic">MycRub a écrit :</a></b><br /><br /><p><span class="u">souligné</span><br /></p></td></tr></table></div><p>
+<br />&nbsp;<br />Une citation :
+<br /></p><div class="container"><table class="quote"><tr class="none"><td><b class="s1">Citation :</b><br /><br /><p>Il fait chaud.<br /></p></td></tr></table></div><p>
+<br />&nbsp;<br />Un spoiler :
+<br /></p><div class="container"><table class="spoiler" onclick="javascript:swap_spoiler_states(this)" style="cursor:pointer;"><tr class="none"><td><b class="s1Topic">Spoiler :</b><br /><br /><div class="Topic masque"><p>Coucou</p></div></td></tr></table></div><p>
+<br />&nbsp;<br />Un bloc fx :
+<br /></p><table class="fixed"><tr class="none"><td><p>Monospace ?</p></td></tr></table><p>
+<br />&nbsp;<br />Du code :
+<br /></p><table class="code"><tr class="none"><td><b class="s1" style="font-family: Verdana, Helvetica, Arial, Sans-serif;">Code :</b><br /><ol id="code1" class="olcode"><li>toto=1;</li><li>tata=2;</li></ol></td></tr></table><p>
+<br />&nbsp;<br />Un email :
+<br /><a rel="nofollow" href="mailto:lolcat@lol.cat" class="cLink">lolcat@lol.cat</a>
+<br />&nbsp;<br />De la couleur :
+<br />Texte <span style="color:#0000FF">bleu</span> et <span style="color:#FF0000">rouge</span><div style="clear: both;"> </div></p></div>"""
+    expected = """Un quote qui contient du souligné:
+[quotemsg=1980038387,0,0][u]souligné[/u][/quotemsg]
+
+Une citation :
+[quote]Il fait chaud.[/quote]
+
+Un spoiler :
+[spoiler]Coucou[/spoiler]
+
+Un bloc fx :
+[fixed]Monospace ?[/fixed]
+
+Du code :
+[code]toto=1;
+tata=2;[/code]
+
+Un email :
+[email]lolcat@lol.cat[/email]
+
+De la couleur :
+Texte [#0000FF]bleu[/#0000FF] et [#FF0000]rouge[/#FF0000]"""
+    output = bb.html_to_bb(input)
+    assert expected == output
+
+    pass