def pushwork2(f_id, feeds):
#区别是自动还是手动处理的
log = logging.getLogger()
#自动
if cmp('http', feeds[0][1][0:4].lower()) == 0:
redbook = BaseFeedBook(log)
redbook.feeds = feeds
else:
#手动
mfeedclasses = FeedClasses()
for mfeed in mfeedclasses:
for my_mfeed in feeds:
if mfeed.__name__ == my_mfeed[1]:
redbook = mfeed(log)
ROOT = path.dirname(path.abspath(__file__))
temp_dir = path.join(ROOT, 'temp')
#创建文件夹
output_dir = path.join(temp_dir, 'feed_%s' % f_id)
isExists = path.exists(output_dir)
if isExists:
rmtree(output_dir)
time.sleep(3)
isExists = path.exists(output_dir)
if not isExists:
os.makedirs(output_dir)
print 'mkdir'
time.sleep(1)
#清空对应的mysql表
model.delete_old_article(f_id)
time.sleep(0.5)
for sec_or_media, url, title, content, brief in redbook.Items():
if sec_or_media.startswith(r'image/'):
filename = path.join(output_dir, title)
fout = open(filename, "wb")
fout.write(content)
fout.close()
else:
model.put_section_article(f_id, sec_or_media, url, title, content,
brief)
#改变更新时间
model.update_article_update_time(f_id)
print '-=end grasp=-'
def GET(self):
username = web.input().get("u")
bookid = web.input().get("id")
user = KeUser.all().filter("name = ", username).get()
if not user:
return "User not exist!<br />"
to = user.kindle_email
if (';' in to) or (',' in to):
to = to.replace(',', ';').replace(' ', '').split(';')
booktype = user.book_type #mobi,epub
bookmode = user.book_mode or 'periodical' #periodical,comic
titlefmt = user.titlefmt
tz = user.timezone
bookid = bookid.split(',') if ',' in bookid else [bookid]
bks = []
for id_ in bookid:
try:
bks.append(Book.get_by_id(int(id_)))
except:
continue
#return "id of book is invalid or book not exist!<br />"
book4meta = None
if len(bks) == 0:
return "No have book to push!"
elif len(bks) == 1:
if bks[0].builtin:
book4meta = BookClass(bks[0].title)
mhfile = book4meta.mastheadfile
coverfile = book4meta.coverfile
if issubclass(book4meta, BaseComicBook
): #如果单独推送一个继承自BaseComicBook的书籍，则自动设置为漫画模式
bookmode = 'comic'
else: #单独的推送自定义RSS
book4meta = bks[0]
mhfile = DEFAULT_MASTHEAD
coverfile = DEFAULT_COVER
else: #多本书合并推送时使用“自定义RSS”的元属性
book4meta = user.ownfeeds
mhfile = DEFAULT_MASTHEAD
coverfile = DEFAULT_COVER_BV if user.merge_books else DEFAULT_COVER
if not book4meta:
return "No have book to push.<br />"
opts = None
oeb = None
# 创建 OEB
#global log
opts = getOpts(user.device, bookmode)
oeb = CreateOeb(main.log, None, opts)
bookTitle = "%s %s" % (book4meta.title, local_time(
titlefmt, tz)) if titlefmt else book4meta.title
if bookmode == 'comic':
pubtype = 'book:book:KindleEar'
else:
pubtype = 'periodical:magazine:KindleEar'
setMetaData(oeb,
bookTitle,
book4meta.language,
local_time("%Y-%m-%d", tz),
pubtype=pubtype)
oeb.container = ServerContainer(main.log)
#guide
if mhfile:
id_, href = oeb.manifest.generate('masthead',
mhfile) # size:600*60
oeb.manifest.add(id_, href, MimeFromFilename(mhfile))
oeb.guide.add('masthead', 'Masthead Image', href)
if coverfile:
imgData = None
imgMime = ''
#使用保存在数据库的用户上传的封面
if coverfile == DEFAULT_COVER and user.cover:
imgData = user.cover
imgMime = 'image/jpeg' #保存在数据库中的只可能是jpeg格式
elif callable(coverfile): #如果封面需要回调的话
try:
imgData = book4meta().coverfile()
if imgData:
imgType = imghdr.what(None, imgData)
if imgType: #如果是合法图片
imgMime = r"image/" + imgType
else:
main.log.warn(
'content of cover is invalid : [%s].' %
bookTitle)
imgData = None
except Exception as e:
main.log.warn(
'Failed to fetch cover for book [%s]. [Error: %s]' %
(bookTitle, str(e)))
coverfile = DEFAULT_COVER
imgData = None
imgMime = ''
if imgData and imgMime:
id_, href = oeb.manifest.generate('cover', 'cover.jpg')
item = oeb.manifest.add(id_, href, imgMime, data=imgData)
else:
id_, href = oeb.manifest.generate('cover', coverfile)
item = oeb.manifest.add(id_, href, MimeFromFilename(coverfile))
oeb.guide.add('cover', 'Cover', href)
oeb.metadata.add('cover', id_)
elif len(bks) > 1 and DEFAULT_COVER:
#将所有书籍的封面拼贴成一个
#如果DEFAULT_COVER=None说明用户不需要封面
id_, href = oeb.manifest.generate('cover', 'cover.jpg')
item = oeb.manifest.add(id_,
href,
'image/jpeg',
data=self.MergeCovers(bks, opts, user))
oeb.guide.add('cover', 'Cover', href)
oeb.metadata.add('cover', id_)
itemcnt, imgindex = 0, 0
sections = OrderedDict()
toc_thumbnails = {} #map img-url -> manifest-href
for bk in bks:
if bk.builtin:
cbook = BookClass(bk.title)
if not cbook:
main.log.warn('not exist book <%s>' % bk.title)
continue
book = cbook(imgindex=imgindex, opts=opts, user=user)
book.url_filters = [flt.url for flt in user.urlfilter]
if bk.needs_subscription: #需要登录
subs_info = user.subscription_info(bk.title)
if subs_info:
book.account = subs_info.account
book.password = subs_info.password
else: # 自定义RSS
if bk.feedscount == 0:
continue #return "the book has no feed!<br />"
book = BaseFeedBook(imgindex=imgindex, opts=opts, user=user)
book.title = bk.title
book.description = bk.description
book.language = bk.language
book.keep_image = bk.keep_image
book.oldest_article = bk.oldest_article
book.fulltext_by_readability = True
feeds = bk.feeds
book.feeds = []
for feed in feeds:
if feed.url.startswith(
("http://www.cartoonmad.com", "http://ac.qq.com",
"http://m.ac.qq.com")):
self.ProcessComicRSS(username, user, feed)
else:
book.feeds.append(
(feed.title, feed.url, feed.isfulltext))
book.url_filters = [flt.url for flt in user.urlfilter]
# 对于html文件，变量名字自文档,thumbnail为文章第一个img的url
# 对于图片文件，section为图片mime,url为原始链接,title为文件名,content为二进制内容,
# img的thumbail仅当其为article的第一个img为True
try: #书的质量可能不一，一本书的异常不能影响其他书籍的推送
for sec_or_media, url, title, content, brief, thumbnail in book.Items(
):
if not sec_or_media or not title or not content:
continue
if sec_or_media.startswith(r'image/'):
id_, href = oeb.manifest.generate(id='img', href=title)
item = oeb.manifest.add(id_,
href,
sec_or_media,
data=content)
if thumbnail:
toc_thumbnails[url] = href
imgindex += 1
else:
#id, href = oeb.manifest.generate(id='feed', href='feed%d.html'%itemcnt)
#item = oeb.manifest.add(id, href, 'application/xhtml+xml', data=content)
#oeb.spine.add(item, True)
sections.setdefault(sec_or_media, [])
sections[sec_or_media].append(
(title, brief, thumbnail, content))
itemcnt += 1
except Exception as e:
excFileName, excFuncName, excLineNo = get_exc_location()
main.log.warn(
"Failed to push <%s> : %s, in file '%s', %s (line %d)" %
(book.title, str(e), excFileName, excFuncName, excLineNo))
continue
volumeTitle = ''
if itemcnt > 0:
#漫画模式不需要TOC和缩略图
if bookmode == 'comic':
insertHtmlToc = False
insertThumbnail = False
if len(bks) == 1 and book: #因为漫画模式没有目录，所以在标题中添加卷号
volumeTitle = book.LastDeliveredVolume()
oeb.metadata.clear('title')
oeb.metadata.add('title', bookTitle + volumeTitle)
else:
insertHtmlToc = GENERATE_HTML_TOC
insertThumbnail = GENERATE_TOC_THUMBNAIL
InsertToc(oeb, sections, toc_thumbnails, insertHtmlToc,
insertThumbnail)
oIO = byteStringIO()
o = EPUBOutput() if booktype == "epub" else MOBIOutput()
o.convert(oeb, oIO, opts, main.log)
try:
ultima_log = DeliverLog.all().order('-time').get()
except:
ultima_log = sorted(DeliverLog.all(),
key=attrgetter('time'),
reverse=True)
ultima_log = ultima_log[0] if ultima_log else None
if ultima_log:
diff = datetime.datetime.utcnow() - ultima_log.datetime
if diff.days * 86400 + diff.seconds < 10:
time.sleep(8)
self.SendToKindle(username, to, book4meta.title + volumeTitle,
booktype, str(oIO.getvalue()), tz)
rs = "%s(%s).%s Sent!" % (book4meta.title, local_time(tz=tz),
booktype)
main.log.info(rs)
return rs
else:
self.deliverlog(username,
str(to),
book4meta.title + volumeTitle,
0,
status='nonews',
tz=tz)
rs = "No new feeds."
main.log.info(rs)
return rs
import os, re, urllib, urlparse, datetime, logging
from config import *
from books.base import BaseFeedBook, BaseUrlBook, WebpageBook
log = logging.getLogger()
feeds = [[u'163easynet', "http://www.xinhuanet.com/ent/news_ent.xml"],
[u'XXXzzhXXX', "http://www.sciencenet.cn/xml/news.aspx?news=0"]]
feeds1 = [[
u'=-=-=asff', 'http://tech.sina.com.cn/i/2014-01-08/08039077686.shtml'
]]
#feeds2=[['324','http://blog.csdn.net/b2b160/article/details/4030702']]
zzh = BaseFeedBook(log, 2)
zzh.feeds = feeds
i = 0
for sec_or_media, url, title, content, brief in zzh.Items():
if sec_or_media.startswith(r'image/'):
filename = 'image/' + title
fout = open(filename, "wb")
fout.write(content)
fout.close()
else:
i += 1
filename = 'image/' + str(i) + '.html'
fout = open(filename, "wb+")
fout.write(content.encode('utf-8'))
fout.close()
