def ParseWorksData(self, page):
temp = page.find(attrs={'class': 'meta'}).findAll('li')
# 07/22/2011 03:09|512×600|RETAS STUDIO
# 07/26/2011 00:30|Manga 39P|ComicStudio 鉛筆 つけペン
# 1/05/2011 07:09|723×1023|Photoshop SAI [ R-18 ]
# 2013年3月16日 06:44 | 800×1130 | Photoshop ComicStudio | R-18
# 2013年12月14日 19:00 855×1133 PhotoshopSAI
self.worksDate = PixivHelper.toUnicode(temp[0].string, encoding=sys.stdin.encoding)
self.worksDateDateTime = PixivHelper.ParseDateTime(self.worksDate, self.dateFormat)
self.worksResolution = unicode(temp[1].string).replace(u'×', u'x')
toolsTemp = page.find(attrs={'class': 'meta'}).find(attrs={'class': 'tools'})
if toolsTemp is not None and len(toolsTemp) > 0:
tools = toolsTemp.findAll('li')
for tool in tools:
self.worksTools = self.worksTools + ' ' + unicode(tool.string)
self.worksTools = self.worksTools.strip()
def ParseInfo(self, page):
self.imageUrls = list()
images = page.findAll(
"div", attrs={"class": "illust-zoom-in thumbnail-container"})
if len(images) > 0:
for image in images:
url = image["data-original-src"]
self.imageUrls.append(url)
self.imageCount = len(self.imageUrls)
if self.imageCount == 1:
self.imageMode = "big"
elif self.imageCount > 1:
self.imageMode = "manga"
else:
# ugoira
canvas = page.find("div",
attrs={"class": "ugoira player-container"})
self.imageMode = "ugoira_view"
url = self.ParseUgoira(canvas["data-ugoira-meta"])
self.imageUrls.append(url)
# title/caption
self.imageTitle = page.findAll("div",
attrs={"class":
"title-container"})[0].text
descriptions = page.findAll(
"div", attrs={"class": "description-text ui-expander-target"})
if len(descriptions) > 0:
self.imageCaption = descriptions[0].text
# view count
self.jd_rtv = int(page.find(attrs={'class': 'react-count'}).text)
# like count
# react-count _clickable illust-bookmark-count-59521621 count like-count
self.jd_rtc = int(
page.find(
attrs={
'class':
re.compile(
r"react-count _clickable illust-bookmark-count-{0} count like-count.*"
.format(self.imageId))
}).text)
# not available
self.jd_rtt = self.jd_rtc
# tags
self.imageTags = list()
# _tag-container tags illust-59521621
tagContainer = page.find("div",
attrs={
"class":
"_tag-container tags illust-{0}".format(
self.imageId)
})
# special node for R-18
r18Tag = page.findAll(attrs={'class': 'tag r-18'})
if r18Tag is not None and len(r18Tag) > 0:
self.imageTags.append("R-18")
tagLinks = tagContainer.findAll("a",
attrs={"class": re.compile(r"tag.*")})
for link in tagLinks:
self.imageTags.append(link["data-activity-tag_name"])
# date
self.worksDate = page.find("li", attrs={"class": "datetime"}).text
self.worksDateDateTime = PixivHelper.ParseDateTime(
self.worksDate, self.dateFormat)
# resolution
# tools
tools = page.findAll("li", attrs={"class": "tool"})
t = list()
for tool in tools:
t.append(tool.text)
if len(t) > 0:
self.worksTools = ", ".join(t)
