Merge pull request #377 from Feng4/patch-5

解决发布日期的问题
This commit is contained in:
Yoshiko2
2020-12-20 21:13:07 +08:00
committed by GitHub

View File

@@ -66,10 +66,17 @@ def getYear(getRelease):
result = '' result = ''
return result return result
def getRelease(a): def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() # html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']") # result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']") # result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+') # return str(result1 + result2).strip('+')
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)</span>')
dates = patherr.findall(a)
if dates:
result = dates[0]
else:
result = ''
return result
def getTag(a): def getTag(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
try: try: