def Items(self,opts=None): """ 生成器，返回一个元组 对于HTML：section,url,title,content,brief 对于图片，mime,url,filename,content,brief """ urls = self.ParseFeedUrls() readability = self.readability if self.fulltext_by_readability else self.readability_by_soup prevsection = '' decoder = AutoDecoder(False) for section,ftitle,url,desc in urls: if not desc:#非全文 if section != prevsection or prevsection == '': decoder.encoding = '' prevsection = section article = self.fetcharticle(url,decoder) if not article: continue else: article = self.FragToXhtml(desc,ftitle) #如果是图片，title则是mime for title, imgurl, imgfn, content, brief in readability(article,url,opts): if title.startswith(r'image/'): #图片 try: content = rescale_image(content,reduceto=(400,600),graying=False) except: content = content yield (title, imgurl, imgfn, content, brief) else: if not title: title = ftitle content = self.postprocess(content) yield (section, url, title, content, brief)
def Items(self, opts=None):
"""
生成器，返回一个元组
对于HTML：section,url,title,content,brief
对于图片，mime,url,filename,content,brief
"""
urls = self.ParseFeedUrls()
readability = self.readability if self.fulltext_by_readability else self.readability_by_soup
prevsection = ''
decoder = AutoDecoder(False)
for section, ftitle, url, desc in urls:
if not desc: #非全文
if section != prevsection or prevsection == '':
decoder.encoding = ''
prevsection = section
article = self.fetcharticle(url, decoder)
if not article:
continue
else:
article = self.FragToXhtml(desc, ftitle)
#如果是图片，title则是mime
for title, imgurl, imgfn, content, brief in readability(
article, url, opts):
if title.startswith(r'image/'): #图片
try:
content = rescale_image(content,
reduceto=(400, 600),
graying=False)
except:
content = content
yield (title, imgurl, imgfn, content, brief)
else:
if not title: title = ftitle
content = self.postprocess(content)
yield (section, url, title, content, brief)
def process_image(self,data,opts): try: if not opts or not opts.process_images or not opts.process_images_immediately: return data elif opts.mobi_keep_original_images: return mobify_image(data) else: return rescale_image(data, png2jpg=opts.image_png_to_jpg, graying=opts.graying_image, reduceto=opts.reduce_image_to) except Exception: return None
def process_image(self, data, opts):
try:
if not opts or not opts.process_images or not opts.process_images_immediately:
return data
elif opts.mobi_keep_original_images:
return mobify_image(data)
else:
return rescale_image(data,
png2jpg=opts.image_png_to_jpg,
graying=opts.graying_image,
reduceto=opts.reduce_image_to)
except Exception:
return None
from lib.img import rescale_image
from lib.url_req import URLOpener
import os
#rescale_image(data, maxsizeb=4000000, dimen=None, png2jpg=False, graying=True, reduceto=(600,800)):
test = URLOpener().open('http://img.xinjunshi.com/uploads/allimg/140224/11-140224101225.jpg')
#test=URLOpener().open('http://www.sucaitianxia.com/d/file/20131222/28caa29d1ddad3c085035e024a9f0b02.png')
con = test.content
con = rescale_image(con,reduceto=(400,600),graying=False)
fout = open('zzh.jpg', "wb")
fout.write(con)
fout.close()
