同步网吧间电脑更改

spiders/MediaSpiders/run.py

@@ -19,4 +19,5 @@ dirpath = os.path.dirname(os.path.abspath(__file__))
 
 sys.path.append(dirpath)
 # 等效于：scrapy crawl FacebookUserSpider -a params="{}"
+# execute(['scrapy', 'crawl', 'LinkedinUserSpider', '-a', 'params={}'])
 execute(['scrapy', 'crawl', 'TwitterUserSpider', '-a', 'params={}'])

spiders/WebsiteSpider/WebsiteSpider/utils/parser_utils.py

@@ -174,7 +174,8 @@ def parse_item_from_response(response, parse_rule, redis_client):
                 else:
                     logger.info(f"翻译成功，标题译文长度：{len(webpage_item['es_abstract'])}")
                     # 翻译内容（按段落，容错）
-                    webpage_item['es_content'] = translate_content_with_paragraphs(webpage_item['es_urlcontent'])
+                    no_tag_content = filter_html_tags(webpage_item['es_urlcontent'], retain_img_br=False)
+                    webpage_item['es_content'] = translate_content_with_paragraphs(no_tag_content)
                     logger.info(f"翻译成功，内容译文长度：{len(webpage_item['es_content'])}")
         except Exception as e:
             logger.error(repr(e))