osc-group/osc
1
1
Fork 0
Code Pull Requests Projects Wiki Activity

同步网吧间电脑更改

Browse Source
This commit is contained in:
DELL 2026-02-12 09:47:28 +08:00
parent 953fdc81dc
commit e4f28c6a89
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
spiders/MediaSpiders/run.py
View File

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

3
spiders/WebsiteSpider/WebsiteSpider/utils/parser_utils.py
View File

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