add 7chan

README.md

@@ -6,7 +6,7 @@ image boards and publishes serialised JSON to RabbitMQ
  
 Compatible image boards: 4chan, lainchan, uboachan,
 22chan, wizchan, 1chan, 2ch.hk, endchan, 38chan, alokal,
-horochan, doushio, desuchan, tgchan, lolnada.
+horochan, doushio, desuchan, tgchan, lolnada, 7chan.
 
 Can optionally push monitoring data to InfluxDB. Below is an
 example of Grafana being used to display it.

chan/chan.py

@@ -1,5 +1,6 @@
 from chan.alokal_json import AlokalJsonChanHelper
 from chan.chan410_html import Chan410HtmlChanHelper
+from chan.chan7_html import Chan7HtmlChanHelper
 from chan.desuchan_html import DesuChanHtmlChanHelper
 from chan.doushio_html import DoushioHtmlChanHelper
 from chan.endchan_html import EndchanHtmlChanHelper
@@ -307,6 +308,23 @@ CHANS = {
         (
             "d", "b", "cu", "dev", "r", "a", "ts", "ci"
         ),
-        rps=1 / 60
+        rps=1 / 120
+    ),
+    "7chan": Chan7HtmlChanHelper(
+        24,
+        "https://7chan.org/",
+        "https://7chan.org/",
+        "/res/",
+        "/src/",
+        (
+            "7ch", "ch7", "irc", "777", "VIP", "civ", "_vip6",
+            "b", "banner", "fl", "gfx", "fail", "class", "co",
+            "eh", "fit", "halp", "jew", "lit", "phi", "pr",
+            "rnb", "sci", "tg", "w", "zom", "a", "grim", "hi",
+            "me", "rx", "vg", "wp", "x", "cake", "cd", "d", "di",
+            "elit", "fag", "fur", "gif", "h", "men", "pco", "s",
+            "sm", "ss", "unf", "v",
+        ),
+        rps=1 / 30
     )
 }

chan/chan7_html.py

@@ -0,0 +1,55 @@
+import datetime
+import re
+from urllib.parse import urljoin
+
+from bs4 import BeautifulSoup
+
+from chan.desuchan_html import DesuChanHtmlChanHelper
+
+
+def _trim_time(text):
+    return re.sub(r"ID: \w+", "", text)
+
+
+class Chan7HtmlChanHelper(DesuChanHtmlChanHelper):
+
+    def parse_threads_list(self, r):
+        soup = BeautifulSoup(r.content.decode('utf-8', 'ignore'), "html.parser")
+
+        threads = []
+
+        for threadEl in soup.find_all("div", class_="thread"):
+            omit = threadEl.find("span", class_="omittedposts")
+            threads.append({
+                "id": int(re.search("thread_([0-9]+)_[a-zA-Z]*", threadEl.get("id")).group(1)),
+                "omit": int(omit.text.split("\n")[1]) if omit else 0
+            })
+
+        for form in soup.find_all("form"):
+            next_button = form.find("input", attrs={"value": "Next"})
+            if next_button and form.get("action") != "none":
+                return threads, urljoin(self._base_url, form.get("action"))
+        return threads, None
+
+    @staticmethod
+    def parse_thread(r):
+        soup = BeautifulSoup(r.content.decode('utf-8', 'ignore'), "html.parser")
+
+        thread_el = soup.find("div", id=lambda x: x and re.match("thread_[0-9]+_[a-zA-Z]*", x))
+        op_el = thread_el.find("div", class_="post")
+        time = "".join(s for s in op_el.find("div", class_="post_header").contents if isinstance(s, str))
+        yield {
+            "id": int(op_el.get("id")),
+            "type": "thread",
+            "html": str(op_el),
+            "time": int(datetime.datetime.strptime(_trim_time(time), "\n%y/%m/%d(%a)%H:%M\n").timestamp())
+        }
+
+        for post_el in thread_el.find_all("div", class_="reply"):
+            time = "".join(s for s in op_el.find("div", class_="post_header").contents if isinstance(s, str))
+            yield {
+                "id": int(post_el.get("id")[6:]),
+                "type": "post",
+                "html": str(post_el),
+                "time": int(datetime.datetime.strptime(_trim_time(time), "\n%y/%m/%d(%a)%H:%M\n").timestamp())
+            }

chan/fchan_html.py

@@ -21,13 +21,9 @@ class FChanHtmlChanHelper(DesuChanHtmlChanHelper):
                 "omit": int(omit.text.split(" ")[0]) if omit and omit.text else 0
             })
 
-        next_url = None
         for a in soup.find_all("a"):
             if a.text == "Next":
-                next_url = a
+                return threads, urljoin(r.url, a.get("href"))
-                break
-        if next_url:
-            return threads, urljoin(r.url, next_url.get("href"))
         return threads, None
 
     @staticmethod

chan/tgchan_html.py

@@ -34,8 +34,7 @@ class TgChanHtmlChanHelper(DesuChanHtmlChanHelper):
         op_el = soup.find("form", id="delform")
 
         for post_el in op_el.find_all("table", recursive=False):
-            label = post_el.find("label")
+            *_, time = post_el.find("label").children
-            *_, time = label.children
             yield {
                 "id": int(post_el.find("td", attrs={"class", "reply"}).get("id")[5:]),
                 "type": "post",