Skip to content

Commit

Permalink
Update wmyblog_coron.py
Browse files Browse the repository at this point in the history
  • Loading branch information
taizihuang authored Sep 7, 2024
1 parent c896362 commit c6108d4
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion wmyblog_coron.py
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,7 @@ def updateBlogData(nTask=20, proxy='',articleUpdate=True,gDriveUpdate=True,comme
# id_list = [d['href'].split('/')[-1] for d in doc.findAll(class_='main-title')][:5]
doc = BeautifulSoup(requests.get(f'https://blog.udn.com/MengyuanWang/article',headers=headers).content, features="lxml")
id_list = [d('a')[0]['href'].split('/')[-1] for d in doc.findAll(class_='article_topic')][:5]
id_list += ['162032391','108908773','171633910','164999328','131394982','108908755','108908678','131174635','125380740','108908753','108908771']
id_list += ['162032391','108908773','171633910','164999328','131394982','108908755','108908678','131174635','125380740','108908753','108908771','178109282']
doc = BeautifulSoup(requests.get(f'https://{domain}/blog/inc_2011/psn_article_ajax.jsp?uid=MengyuanWang&f_FUN_CODE=new_rep',headers=headers).content, features="lxml")
id_list = id_list + [d('a')[0]['href'].split('/')[-1] for d in doc.findAll('dt')]
id_list += list(pd.read_pickle('./data/comment_full.pkl').id.iloc[:20])
Expand Down

0 comments on commit c6108d4

Please sign in to comment.