def _parse_attachment_ids_request_query(self, page, since=None):
# Formats
digits = re.compile("\d+")
attachment_href = re.compile("attachment.cgi\?id=\d+&action=review")
# if no date is given, return all ids
if not since:
attachment_links = SoupStrainer("a", href=attachment_href)
return [
int(digits.search(tag["href"]).group(0))
for tag in BeautifulSoup(page, parseOnlyThese=attachment_links)
]
# Parse the main table only
date_format = re.compile("\d{4}-\d{2}-\d{2} \d{2}:\d{2}")
mtab = SoupStrainer("table", {"class": "requests"})
soup = BeautifulSoup(page, parseOnlyThese=mtab)
patch_ids = []
for row in soup.findAll("tr"):
patch_tag = row.find("a", {"href": attachment_href})
if not patch_tag:
continue
patch_id = int(digits.search(patch_tag["href"]).group(0))
date_tag = row.find("td", text=date_format)
if date_tag and datetime.strptime(
date_format.search(date_tag).group(0),
"%Y-%m-%d %H:%M") < since:
continue
patch_ids.append(patch_id)
return patch_ids
def _parse_attachment_ids_request_query(self, page):
digits = re.compile("\d+")
attachment_href = re.compile("attachment.cgi\?id=\d+&action=review")
attachment_links = SoupStrainer("a", href=attachment_href)
return [
int(digits.search(tag["href"]).group(0))
for tag in BeautifulSoup(page, parseOnlyThese=attachment_links)
]