Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/icoz/habraparse.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authoricoz <icoz.vt@gmail.com>2019-08-26 23:35:56 +0300
committericoz <icoz.vt@gmail.com>2019-08-26 23:35:56 +0300
commitc14ffeede5406810afacf7f06f24775246018bdf (patch)
tree9ce566451526885fff7189e9823750ea99235ccf
parent4fbdd3ddd52aae6ed319c458bed94298cdbb8ad4 (diff)
Небольшие правки при парсинге комментов 2
-rw-r--r--habr/topic.py4
1 files changed, 0 insertions, 4 deletions
diff --git a/habr/topic.py b/habr/topic.py
index 2a5b903..e3abc69 100644
--- a/habr/topic.py
+++ b/habr/topic.py
@@ -93,8 +93,6 @@ class TMTopic(object):
self.post['text'] = etree.tostring(tmp[0], pretty_print=True, method='html').decode('utf-8') if len(tmp) else ''
# get comments
self.post['comments'] = []
- # for cmnt in doc.xpath("//ul[@id='comments-list']//li[@class='content-list__item content-list__item_comment js-comment ']"):
- # for cmnt in doc.xpath("//div[@class='tm-page-article-comments__inner']//div[@class='tm-comments-list__comment']"):
for cmnt in doc.xpath("//ul[@id='comments-list']//li[@class='content-list__item content-list__item_comment js-comment ']"):
try:
cmnt_text = cmnt.find_class('comment__message')
@@ -106,8 +104,6 @@ class TMTopic(object):
{
'author': cmnt.find_class("user-info__nickname")[0].text, # if cmnt.find_class("user-info__nickname") else "",
'text': cmnt_text,
- # if cmnt.find_class('comment__message') else "",
- # 'text': cmnt.find_class('comment__message')[0].text, # if cmnt.find_class('comment__message') else "",
'c_id': int(cmnt.attrib['rel']),
'p_id': int(cmnt.find_class("parent_id")[0].attrib['data-parent_id']),
'time': cmnt.find_class('comment__date-time')[0].text