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

Merge remote-tracking branch 'origin/master'

Browse Source 
# Conflicts:
#	scrapinglib/fanza.py
This commit is contained in:
Wayne.S.Lui
2022-08-31 14:17:52 +08:00
parent 593fb99723
commit 4502167216
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
scrapinglib/fanza.py
View File

@@ -139,8 +139,9 @@ class Fanza(Parser):
return result return result
def getExtrafanart(self, htmltree): def getExtrafanart(self, htmltree):
htmltext = re.search(r'<div id=\"sample-image-block\"[\s\S]*?<br></div>\s*?</div>', self.htmlcode).group() htmltext = re.search(r'<div id=\"sample-image-block\"[\s\S]*?<br></div>\s*?</div>', self.htmlcode)
if htmltext: if htmltext:
htmltext = htmltext.group()
extrafanart_images = re.findall(r'<img.*?src=\"(.*?)\"', htmltext) extrafanart_images = re.findall(r'<img.*?src=\"(.*?)\"', htmltext)
if extrafanart_images: if extrafanart_images:
sheet = [] sheet = []
@@ -151,10 +152,12 @@ class Fanza(Parser):
return '' return ''
def getTrailer(self, htmltree): def getTrailer(self, htmltree):
htmltext = re.search(r'<script type=\"application/ld\+json\">[\s\S].*}\s*?</script>', self.htmlcode).group() htmltext = re.search(r'<script type=\"application/ld\+json\">[\s\S].*}\s*?</script>', self.htmlcode)
if htmltext: if htmltext:
url = re.search(r'\"contentUrl\":\"(.*?)\"', htmltext).group(1) htmltext = htmltext.group()
url = re.search(r'\"contentUrl\":\"(.*?)\"', htmltext)
if url: if url:
url = url.group(1)
url = url.rsplit('_', 2)[0] + '_mhb_w.mp4' url = url.rsplit('_', 2)[0] + '_mhb_w.mp4'
return url return url
return '' return ''