bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #373 from Feng4/patch-2

Browse Source 
解决发布时间抓取不到的问题
This commit is contained in:
Yoshiko2
2020-12-19 21:56:55 +08:00
committed by GitHub
parent bc85a19eda 7efc96f27d
commit fcd782f72d
1 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
WebCrawler/javdb.py
View File

@@ -26,10 +26,17 @@ def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
d.update(p)
return d
def getStudio(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
# html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
# result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
# return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
patherr = re.compile(r'<strong>片商\:</strong>[\s\S]*?<a href=\".*?>(.*?)</a></span>')
pianshang = patherr.findall(a)
if pianshang:
result = pianshang[0]
else:
result = ""
return result
def getRuntime(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時長")]/../span/text()')).strip(" ['']")
@@ -46,11 +53,18 @@ def getNum(a):
result2 = str(html.xpath('//strong[contains(text(),"番號")]/../span/a/text()')).strip(" ['']")
return str(result2 + result1).strip('+')
def getYear(getRelease):
try:
result = str(re.search('\d{4}', getRelease).group())
return result
except:
return getRelease
# try:
# result = str(re.search('\d{4}', getRelease).group())
# return result
# except:
# return getRelease
patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)\-.*?</span>')
dates = patherr.findall(getRelease)
if dates:
result = dates[0]
else:
result = ''
return result
def getRelease(a):
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")