From 527bdb190c0681c4a759900bf5ad1c7d6425575e Mon Sep 17 00:00:00 2001
From: hillerliao <liaomeigu@gmail.com>
Date: Sat, 29 Feb 2020 10:56:43 +0800
Subject: [PATCH] scrc audit status crawler

---
 rsshub/blueprints/main.py        |  5 +++++
 rsshub/spiders/csrc/audit.py     | 38 ++++++++++++++++++++++++++++++++
 rsshub/templates/main/feeds.html | 13 +++++++++++
 3 files changed, 56 insertions(+)
 create mode 100644 rsshub/spiders/csrc/audit.py

diff --git a/rsshub/blueprints/main.py b/rsshub/blueprints/main.py
index 83d4908..46da12f 100644
--- a/rsshub/blueprints/main.py
+++ b/rsshub/blueprints/main.py
@@ -84,4 +84,9 @@ def earningsdate_businesswire():
 @bp.route('/jiemian/newsflash/<string:category>')
 def jiemian_newsflash(category=''):
     from rsshub.spiders.jiemian.newsflash import ctx
+    return render_template('main/atom.xml', **filter_content(ctx(category)))
+
+@bp.route('/csrc/audit/<string:category>')
+def csrc_audit(category=''):
+    from rsshub.spiders.csrc.audit import ctx
     return render_template('main/atom.xml', **filter_content(ctx(category)))
\ No newline at end of file
diff --git a/rsshub/spiders/csrc/audit.py b/rsshub/spiders/csrc/audit.py
new file mode 100644
index 0000000..2e1f852
--- /dev/null
+++ b/rsshub/spiders/csrc/audit.py
@@ -0,0 +1,38 @@
+import requests
+from parsel import Selector
+
+domain = 'https://neris.csrc.gov.cn'
+
+
+def parse(post):
+    item = {}
+    item['title'] = post.css('li.templateTip').css('li::text').extract_first()
+    audit_status = post.css('td[style="font-weight:100 ;color: black ;position: relative;left:20px"]').css('td::text').extract()
+    audit_date = post.css('td[style="font-weight:100 ;color:black;position: relative; "]').css('td::text').extract()
+    
+    description = item['title'] + '；'
+    for i in range(len(audit_status)):
+        description += '<' + audit_date[i] + ' ' + audit_status[i] + '>\n'
+
+    item['title'] += '，' + audit_status[-1]
+    item['description'] = description
+    item['pubDate'] = audit_date[-1]
+    return item
+
+
+def ctx(category=''):
+    q_url = f"{domain}/alappl/home1/onlinealog.do"
+    items = []
+    for i in range(1,4):
+        q_data = {"appMatrCde": category, "pageNo": str(i), "pageSize": "10"}
+        res = requests.post(q_url,data=q_data, verify=False)
+        tree = Selector(res.text)
+        posts = tree.css('tr[height="50"]')
+        items.extend(list(map(parse, posts)))
+    return {
+        'title': f'申请事项进度查询 - {category}  - 中国证监会',
+        'link': f'{domain}/alappl/home1/onlinealog?appMatrCde={category}',
+        'description': f'{category} 申请事项进度查询 - 中国证监会',
+        'author': 'hillerliao',
+        'items': items
+    }
diff --git a/rsshub/templates/main/feeds.html b/rsshub/templates/main/feeds.html
index 14cc221..c23112b 100644
--- a/rsshub/templates/main/feeds.html
+++ b/rsshub/templates/main/feeds.html
@@ -111,4 +111,17 @@
 </div>
 <br>
 <!--item info end-->
+
+<!--item info start-->
+<div class="card text-left">
+  <div class="card-body">
+    <h4 class="card-title">证监会审核进度</h4>
+    <h6 class="text-muted">证监会审核进度 <a href="https://github.com/hillerliao" target="_blank" class="badge badge-secondary">by hillerliao</a></h6>
+    <p class="card-text">举例：<a href="https://rsshub-python.herokuapp.com/csrc/audit/a1d50077cd7f4b15bd1c8d6163f32850" target="_blank">https://rsshub-python.herokuapp.com/csrc/audit/a1d50077cd7f4b15bd1c8d6163f32850</a></p>
+    <p class="card-text">路由：<code>/csrc/audit/:category</code></p>
+    <p class="card-text">参数：category [必填，见证监会栏目 https://neris.csrc.gov.cn/alappl/home/gongshi]</p>
+  </div>
+</div>
+<br>
+<!--item info end-->
 {% endblock content %}
\ No newline at end of file