feat:ins爬虫数据条件过滤优化

config/settings.py

@@ -4,7 +4,7 @@ def get_log_path():
 
 
 def get_base_url():
-    return "http://192.168.0.118:8081/"
+    return "http://192.168.0.104:8081/"
 
 
 def get_base_file_url():

pc_instagram.py

@@ -72,7 +72,8 @@ def reptile(browser=None, search_word=""):
         wait.until(EC.presence_of_element_located((By.XPATH, "//div[@role='dialog']/div/div[2]")))
 
         # 提取其他
-        author = browser.find_element("xpath", "//div[@role='dialog']/div//article/div/div[2]/div/div/div[1]//a")
+        author = browser.find_element("xpath",
+                                      "//div[@role='dialog']/div//article/div/div[2]/div/div/div[1]/div/header/div[2]/div[1]/div[1]//a")
 
         content_element = browser.find_element("xpath",
                                                "//div[@role='dialog']/div//article/div/div[2]/div/div/div[2]/div[1]//div[@role='button']//h1")
@@ -90,21 +91,35 @@ def reptile(browser=None, search_word=""):
         # 过滤视频
         video_list = browser.find_elements("xpath", "//div[@role='dialog']/div//article/div/div[1]/div/div[1]//video")
         for key, item in enumerate(img_list):
+            src = ""
+            img_soup = ""
             if len(video_list) == 0:
                 if key == 0:
-                    title = item.get_attribute("alt")
-                # 下载图片至本地，替换标签中的src
-                id = str(int(time.time()))
+                    title_str_list = item.get_attribute("alt").split("'")
+                    if len(title_str_list) >= 3:
+                        title = title_str_list[2]
+                    else:
+                        title = ""
+                img_soup = BeautifulSoup(item.get_attribute("outerHTML"), "html.parser").find("img")
+                src = item.get_attribute("src")
+            else:
+                # 有视频，图片链接从列表中提取
+                title = ""
+                a_soup = BeautifulSoup(element_link_list[index].get_attribute("outerHTML"), "html.parser")
+                # img_element = element_link_list[index].find_element("xpath","img")
+                img_soup = a_soup.find("img")
+                src = img_soup["src"]
+            str_list = link_str.split("/")
+            img_id = str_list[len(str_list) - 2]
             # 下载地址
-                download_dir = f'{os.path.join(file_dir, f"{id}.jpg")}'
+            download_dir = f'{os.path.join(file_dir, f"{img_id}.jpg")}'
             # 访问地址
-                access_address = f'{get_base_file_url()}{table_name.split("_")[1]}/{id}.jpg'
+            access_address = f'{get_base_file_url()}{table_name.split("_")[1]}/{img_id}.jpg'
             # 下载状态
-                status = download_image(item.get_attribute("src"), download_dir)
+            status = download_image(src, download_dir)
             if status:
                 # 将图片追加到内容中
-                    img_soup = BeautifulSoup(item.get_attribute("outerHTML"), "html.parser")
-                    img_soup.img["src"] = access_address
+                img_soup["src"] = access_address
                 # print(img_soup.prettify())
                 soup.append(img_soup)
                 picture_url.append(access_address)
@@ -176,7 +191,7 @@ def main():
         log.debug("call success")
         search_word = ""
         for item in response['data']['rows']:
-            if item['name'] == 'pms_instagram':
+            if item['name'] == 'instagram':
                 search_word = item['keyword']
                 table_name = item['tableName']
                 status_task = int(item["status"])