Merge pull request #108 from Guovin/dev

Release: v1.1.3

.github/workflows/main.yml

@@ -18,7 +18,7 @@ jobs:
     steps:
       - name: Set branch name
         id: vars
-        run: echo ::set-output name=branch::${{ github.repository_owner == 'Guovin' && 'gd' || 'master' }}
+        run: echo "branch=${{ github.repository_owner == 'Guovin' && 'gd' || 'master' }}" >> $GITHUB_ENV
       - uses: actions/checkout@v3
         with:
           ref: ${{ steps.vars.outputs.branch }}

CHANGELOG.md

@@ -1,5 +1,13 @@
 # 更新日志（Changelog）
 
+## v1.1.3
+
+### 2024/5/8
+
+- 优化频道接口不对应问题（#99）（Optimize the mismatch problem of the channel interface (#99)）
+- 处理 tqdm 安全问题（Handle the security issue of tqdm）
+- 修改即将被废弃的命令（Modify the commands that are about to be deprecated）
+
 ## v1.1.2
 
 ### 2024/5/7

Pipfile

@@ -16,7 +16,7 @@ selenium = "4.19.0"
 selenium-stealth = "1.0.6"
 aiohttp = ">=3.9.4"
 bs4 = "0.0.2"
-tqdm = "4.66.2"
+tqdm = ">=4.66.3"
 async-timeout = "4.0.3"
 
 [requires]

main.py

@@ -8,13 +8,12 @@
 from selenium.webdriver.support import expected_conditions as EC
 from selenium_stealth import stealth
 import asyncio
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup
 from utils import (
     getChannelItems,
     updateChannelUrlsTxt,
     updateFile,
-    getChannelUrl,
-    getChannelInfo,
+    getResultsFromSoup,
     sortUrlsBySpeedAndResolution,
     getTotalUrls,
     filterUrlsByPatterns,
@@ -124,25 +123,7 @@ async def visitPage(self, channelItems):
                             )
                             soup = BeautifulSoup(source, "html.parser")
                             if soup:
-                                results = []
-                                for element in soup.descendants:
-                                    if isinstance(element, NavigableString):
-                                        url = getChannelUrl(element)
-                                        if url and not any(
-                                            item[0] == url for item in results
-                                        ):
-                                            url_element = soup.find(
-                                                lambda tag: tag.get_text(strip=True)
-                                                == url
-                                            )
-                                            if url_element:
-                                                info_element = (
-                                                    url_element.find_next_sibling()
-                                                )
-                                                date, resolution = getChannelInfo(
-                                                    info_element
-                                                )
-                                                results.append((url, date, resolution))
+                                results = getResultsFromSoup(soup, name)
                                 for result in results:
                                     url, date, resolution = result
                                     if url and checkUrlByPatterns(url):

utils.py

@@ -13,6 +13,7 @@
 from urllib.parse import urlparse
 import requests
 import re
+from bs4 import NavigableString
 
 
 def getChannelItems():
@@ -44,16 +45,12 @@ def getChannelItems():
                 # This is a url, add it to the list of urls for the current channel.
                 match = re.search(pattern, line)
                 if match is not None:
-                    if match.group(1) not in channels[current_category]:
-                        channels[current_category][match.group(1)] = [match.group(2)]
-                    elif (
-                        match.group(2)
-                        and match.group(2)
-                        not in channels[current_category][match.group(1)]
-                    ):
-                        channels[current_category][match.group(1)].append(
-                            match.group(2)
-                        )
+                    name = match.group(1).strip()
+                    url = match.group(2).strip()
+                    if name not in channels[current_category]:
+                        channels[current_category][name] = [url]
+                    elif url and url not in channels[current_category][name]:
+                        channels[current_category][name].append(url)
         return channels
     finally:
         f.close()
@@ -171,6 +168,45 @@ def getChannelInfo(element):
     return date, resolution
 
 
+def checkNameMatch(name, result_name):
+    pattern = r"[a-zA-Z]+[_\-+]|cctv"
+    if re.search(
+        pattern,
+        result_name,
+        re.IGNORECASE,
+    ):
+        print(
+            "Name test match:",
+            name.lower(),
+            result_name.lower(),
+            name.lower() == result_name.lower(),
+        )
+        return name.lower() == result_name.lower()
+    else:
+        return True
+
+
+def getResultsFromSoup(soup, name):
+    """
+    Get the results from the soup
+    """
+    results = []
+    for element in soup.descendants:
+        if isinstance(element, NavigableString):
+            url = getChannelUrl(element)
+            if url and not any(item[0] == url for item in results):
+                url_element = soup.find(lambda tag: tag.get_text(strip=True) == url)
+                if url_element:
+                    name_element = url_element.find_previous_sibling()
+                    if name_element:
+                        channel_name = name_element.get_text(strip=True)
+                        if checkNameMatch(name, channel_name):
+                            info_element = url_element.find_next_sibling()
+                            date, resolution = getChannelInfo(info_element)
+                            results.append((url, date, resolution))
+    return results
+
+
 async def getSpeed(url, urlTimeout=5):
     """
     Get the speed of the url

version.json

@@ -1,3 +1,3 @@
 {
-  "version": "1.1.2"
+  "version": "1.1.3"
 }