diff --git a/CHANGELOG-zh.md b/CHANGELOG-zh.md index d0f85f2a..34d53b06 100644 --- a/CHANGELOG-zh.md +++ b/CHANGELOG-zh.md @@ -1,3 +1,16 @@ +# 0.4.5 (unkown) +### 功能 / 优化 +- **交互式教程**. 引导用户了解 Crawlab 的主要功能. + +### Bug 修复 +- **点击删除按钮导致跳转**. [#480](https://github.com/crawlab-team/crawlab/issues/480) +- **无法在空爬虫里创建文件**. [#479](https://github.com/crawlab-team/crawlab/issues/479) +- **下载结果错误**. [#465](https://github.com/crawlab-team/crawlab/issues/465) +- **crawlab-sdk CLI 错误**. [#458](https://github.com/crawlab-team/crawlab/issues/458) +- **页面刷新问题**. [#441](https://github.com/crawlab-team/crawlab/issues/441) +- **修复“删除爬虫后获取所有爬虫”错误**. +- **修复 i18n warning 警告**. + # 0.4.4 (2020-01-17) ### 功能 / 优化 diff --git a/CHANGELOG.md b/CHANGELOG.md index c7d5f6e5..182df69f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,16 @@ +# 0.4.5 (unkown) +### Features / Enhancement +- **Interactive Tutorial**. Guide users through the main functionalities of Crawlab. + +### Bug Fixes +- **Click delete button results in redirect**. [#480](https://github.com/crawlab-team/crawlab/issues/480) +- **Unable to create files in an empty spider**. [#479](https://github.com/crawlab-team/crawlab/issues/479) +- **Download results error**. [#465](https://github.com/crawlab-team/crawlab/issues/465) +- **crawlab-sdk CLI error**. [#458](https://github.com/crawlab-team/crawlab/issues/458) +- **Page refresh issue**. [#441](https://github.com/crawlab-team/crawlab/issues/441) +- **Getting all spider after deleting a spider**. +- **i18n warning**. + # 0.4.4 (2020-01-17) ### Features / Enhancement - **Email Notification**. Allow users to send email notifications. diff --git a/backend/template/scrapy/config_spider/spiders/spider.py b/backend/template/scrapy/config_spider/spiders/spider.py index 0e3c661d..d87f4297 100644 --- a/backend/template/scrapy/config_spider/spiders/spider.py +++ b/backend/template/scrapy/config_spider/spiders/spider.py @@ -2,11 +2,14 @@ import scrapy import re from config_spider.items import Item -from urllib.parse import urljoin +from urllib.parse import urljoin, urlparse def get_real_url(response, url): - if re.search(r'^https?|^\/\/', url): + if re.search(r'^https?', url): return url + elif re.search(r'^\/\/', url): + u = urlparse(response.url) + return u.scheme + url return urljoin(response.url, url) class ConfigSpider(scrapy.Spider): diff --git a/frontend/src/components/Config/ConfigList.vue b/frontend/src/components/Config/ConfigList.vue index b1a10941..fff81080 100644 --- a/frontend/src/components/Config/ConfigList.vue +++ b/frontend/src/components/Config/ConfigList.vue @@ -1,5 +1,14 @@