Merge branch 'master' of https://le-club-des-sans-sujets.org:7777/gauthiier/listservs
??? trying to merge after a year???
This commit is contained in:
commit
9c4cdb72ad
@ -263,7 +263,7 @@ class Archive:
|
||||
return results
|
||||
|
||||
except mariadb.Error as error:
|
||||
logging.erro("Error: {}".format(error))
|
||||
logging.error("Error: {}".format(error))
|
||||
finally:
|
||||
cursor.close()
|
||||
|
||||
|
||||
@ -203,15 +203,18 @@ def collect_message(url, message):
|
||||
# message['author_name'] = from_addr[0]
|
||||
# message['from'] = from_addr[1]
|
||||
|
||||
## -- content --
|
||||
# test
|
||||
c1 = soup.select('pre:nth-of-type(1)')
|
||||
if len(c1) > 0:
|
||||
message['content'] = c1[0].text
|
||||
else:
|
||||
message['content'] = soup.select('pre:nth-of-type(2)')[0].text
|
||||
# ## -- content --
|
||||
# # test
|
||||
# c1 = soup.select('pre:nth-of-type(1)')
|
||||
# if len(c1) > 0:
|
||||
# message['content'] = c1[0].text
|
||||
# else:
|
||||
# message['content'] = soup.select('pre:nth-of-type(2)')[0].text
|
||||
|
||||
# message['content'] = soup.select('pre:nth-of-type(2)')[0].text
|
||||
# # message['content'] = soup.select('pre:nth-of-type(2)')[0].text
|
||||
|
||||
# new way!
|
||||
message['content'] = parse_xmessage(str(soup))
|
||||
|
||||
# mhonarc xcomments
|
||||
# ref: http://www.schlaubert.de/MHonArc/doc/resources/printxcomments.html
|
||||
@ -223,3 +226,11 @@ def parse_xcomment(soup, xcom):
|
||||
|
||||
def test_xcomment(soup):
|
||||
return soup.find(text=re.compile('X-Message-Id')) is not None
|
||||
|
||||
# (edit 21.12.2019): this is the new way as of 2018 -- when no more moderation on Nettime...
|
||||
def parse_xmessage(html):
|
||||
rr = r'<!--X-Body-of-Message-->.*?<!--X-Body-of-Message-End-->'
|
||||
s = re.search(rr, html, re.DOTALL)
|
||||
se = BeautifulSoup(s.group(), "html5lib")
|
||||
return se.get_text()
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user