diff --git a/.buildinfo b/.buildinfo index 042eb56..6896f8b 100644 --- a/.buildinfo +++ b/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 496c554a013a2b9a9fa47504ea006d82 +config: f744698d55f38bf171e6cd3e48afa688 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/_modules/index.html b/_modules/index.html index 7297fbf..7223d00 100644 --- a/_modules/index.html +++ b/_modules/index.html @@ -5,7 +5,7 @@ - 概览：模块代码 — xhs 0.2.10 文档 + 概览：模块代码 — xhs 0.2.11 文档 diff --git a/_modules/xhs/core.html b/_modules/xhs/core.html index 641dca1..a839712 100644 --- a/_modules/xhs/core.html +++ b/_modules/xhs/core.html @@ -5,7 +5,7 @@ - xhs.core — xhs 0.2.10 文档 + xhs.core — xhs 0.2.11 文档 @@ -43,7 +43,8 @@

xhs.core 源代码

 import requests
 from lxml import etree
 
-from xhs.exception import DataFetchError, ErrorEnum, IPBlockError, SignError
+from xhs.exception import (DataFetchError, ErrorEnum, IPBlockError,
+                           NeedVerifyError, SignError)
 
 from .help import (cookie_jar_to_cookie_str, download_file,
                    get_imgs_url_from_note, get_search_id, get_valid_path_name,
@@ -200,12 +201,17 @@ 
xhs.core 源代码
             return response
         if data.get("success"):
             return data.get("data", data.get("success"))
-        elif data["code"] == ErrorEnum.IP_BLOCK.value.code:
-            raise IPBlockError(ErrorEnum.IP_BLOCK.value.msg)
-        elif data["code"] == ErrorEnum.SIGN_FAULT.value.code:
-            raise SignError(ErrorEnum.SIGN_FAULT.value.msg)
+        elif response.status_code == 471:
+            # someday someone maybe will bypass captcha
+            raise NeedVerifyError(
+                f"出现验证码，请求失败，Verifytype: {response.headers['Verifytype']}，Verifyuuid: {response.headers['Verifyuuid']}",
+                response=response)
+        elif data.get("code") == ErrorEnum.IP_BLOCK.value.code:
+            raise IPBlockError(ErrorEnum.IP_BLOCK.value.msg, response=response)
+        elif data.get("code") == ErrorEnum.SIGN_FAULT.value.code:
+            raise SignError(ErrorEnum.SIGN_FAULT.value.msg, response=response)
         else:
-            raise DataFetchError(data)

+            raise DataFetchError(data, response=response)
[文档] def get(self, uri: str, params=None, is_creator: bool = False, **kwargs): final_uri = uri @@ -266,7 +272,7 @@

xhs.core 源代码

             return dict_new
 
         url = "https://www.xiaohongshu.com/explore/" + note_id
-        res = self.session.get(url, headers={"user-agent": self.user_agent})
+        res = self.session.get(url, headers={"user-agent": self.user_agent, "referer": "https://www.xiaohongshu.com/"})
         html = res.text
         state = re.findall(r"window.__INITIAL_STATE__=({.*})</script>", html)[
             0
@@ -912,8 +918,7 @@ 
xhs.core 源代码
         headers = {
             "Referer": "https://creator.xiaohongshu.com/"
         }
-        print(data)
-        return self.post(uri, data, headers=headers, is_creator=True)

+        return self.post(uri, data, headers=headers)
[文档] def create_image_note( self, @@ -973,7 +978,6 @@

xhs.core 源代码

         )
 
         res = response.json()
-        print(res)
         if res["data"]["hasFirstFrame"]:
             image_id = res["data"]["firstFrameFileId"]
             return image_id
diff --git a/_static/documentation_options.js b/_static/documentation_options.js
index 08d37ca..dcb085e 100644
--- a/_static/documentation_options.js
+++ b/_static/documentation_options.js
@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '0.2.10',
+    VERSION: '0.2.11',
     LANGUAGE: 'zh_CN',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',
diff --git a/basic.html b/basic.html
index f6948b5..242a59d 100644
--- a/basic.html
+++ b/basic.html
@@ -5,7 +5,7 @@
   
     
     
-    快速入门 — xhs 0.2.10 文档
+    快速入门 — xhs 0.2.11 文档
     
     
     
diff --git a/crawl.html b/crawl.html
index 9139c1e..ec11ca1 100644
--- a/crawl.html
+++ b/crawl.html
@@ -5,7 +5,7 @@
   
     
     
-    主页爬取 — xhs 0.2.10 文档
+    主页爬取 — xhs 0.2.11 文档
     
     
     
diff --git a/creator.html b/creator.html
index 0be72cb..c09f4e8 100644
--- a/creator.html
+++ b/creator.html
@@ -5,7 +5,7 @@
   
     
     
-    笔记发布 — xhs 0.2.10 文档
+    笔记发布 — xhs 0.2.11 文档
     
     
     
diff --git a/genindex.html b/genindex.html
index 484a249..3cf2db0 100644
--- a/genindex.html
+++ b/genindex.html
@@ -5,7 +5,7 @@
   
     
     
-    索引 — xhs 0.2.10 文档
+    索引 — xhs 0.2.11 文档
     
     
     
diff --git a/index.html b/index.html
index 896a2dd..45144f5 100644
--- a/index.html
+++ b/index.html
@@ -5,7 +5,7 @@
   
     
     
-    介绍 — xhs 0.2.10 文档
+    介绍 — xhs 0.2.11 文档
     
     
     
diff --git a/search.html b/search.html
index 0631c4f..c81784e 100644
--- a/search.html
+++ b/search.html
@@ -5,7 +5,7 @@
   
     
     
-    搜索 — xhs 0.2.10 文档
+    搜索 — xhs 0.2.11 文档
     
     
     
diff --git a/source/xhs.html b/source/xhs.html
index ce281c0..8a3c8cc 100644
--- a/source/xhs.html
+++ b/source/xhs.html
@@ -5,7 +5,7 @@
   
     
     
-    Documentation — xhs 0.2.10 文档
+    Documentation — xhs 0.2.11 文档