def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=Spider.ComposeUrl(self.url, x[0]),
title=x[1],
time=datetime.datetime.strptime(x[2], '%Y-%m-%d'))
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(
article['url'],
urllib.parse.quote(z) if z[0] in ['/', '.'] else z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
image['imageUrl'] = Spider.ComposeUrl(article['url'], z)
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=Spider.ComposeUrl(self.url, x[0]), title=x[1])
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
article['time'] = datetime.datetime.strptime(y[0], '%Y-%m-%d')
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
content = y[1]
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(
time=datetime.datetime.strptime(x[0], '%Y-%m-%d'),
# url = self.url[0:self.url.rfind('/')] + x[1][1:],
url=Spider.ComposeUrl(self.url, x[1]),
title=x[2])
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
# imageUrl = article['url'][0:article['url'].rfind('/')] + z[1:]
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recPage = re.compile(
'<OPTION value=([^>\s]+?)(?:\s[^>]*?)*?>[^<]*?</OPTION>',
re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=Spider.ComposeUrl(self.url, x[0]),
title=x[1],
time=datetime.datetime.strptime(x[2], '%Y-%m-%d'))
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
totalContent = ''
images = []
imageCount = 0
pageUrls = recPage.findall(html)
if len(pageUrls) == 0:
pageUrls += [article['url']]
for p in pageUrls:
pageUrl = Spider.ComposeUrl(article['url'], p)
if pageUrl != article['url']:
html = self.DownLoadHtml(pageUrl, '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl,
'图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if content != None:
totalContent += content
if totalContent == '' \
or imageCount != len(images):
continue
self.CacheArticle(article, totalContent, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
abstracts = None
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章摘要接口{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
try:
html = html.replace('null', 'None')
abstracts = eval(html)
except Exception as e:
logging.warn('文章摘要信息{0}格式异常，异常信息为:{1}'.format(html, str(e)))
return self.articles
for x in abstracts['contents']:
try:
article = dict(url=Spider.ComposeUrl(
self.url, '/{0}/{1}.jhtml'.format(x['channel_path'],
x['contentId'])),
title=x['title'])
html = super().DownLoadHtml(article['url'],
'文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
article['time'] = datetime.datetime.strptime(
y[0], '%Y-%m-%d %H:%M:%S')
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
content = y[1]
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl,
'图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
except Exception as e:
logging.warn('文章明细信息{0}格式异常，异常信息为:{1}'.format(str(x), str(e)))
continue
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recDate = re.compile('Details([\d-]+?).html', re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(
url = Spider.ComposeUrl(self.url, x[0]),
title = x[1].strip()
)
for w in recDate.findall(article['url']):
try:
article['time'] = datetime.datetime.strptime('20{0}'.format(w[0:8]),
'%Y-%m-%d')
except Exception as e:
logging.warn('文章源{0}无法识别发布日期，异常为:{1}'.format(article['url'],
str(e)))
continue
# logging.debug(str(article))
if not 'time' in article:
#不符合格式的外部链接忽略
continue
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recDate = re.compile('http://www.gotohz.com/\w+?/\w+?/\d+?/t(\d+?)_\d+?.shtml', re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(
title = x[0],
url = Spider.ComposeUrl(self.url, x[1])
)
for w in recDate.findall(article['url']):
article['time'] = datetime.datetime.strptime(w,'%Y%m%d')
# logging.debug(str(article))
if not 'time' in article:
#不符合格式的外部链接忽略
continue
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recKeyword = re.compile(self.reKeyword, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=xml.sax.saxutils.unescape(
Spider.ComposeUrl(self.url, x[0])),
title=x[1].strip(),
time=datetime.datetime.strptime(x[2], '%Y-%m-%d'))
#关键词检查
if recKeyword.match(x[1]) == None:
continue
else:
logging.debug('文章Url为{0}, 标题为{1}。'.format(
article['url'], article['title']))
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
validUrl = 'http://news.cncn.com/'
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}', 'gbk')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(time=datetime.datetime.strptime(
'{0}-01-01'.format(datetime.datetime.today().year),
'%Y-%m-%d'),
url=Spider.ComposeUrl(self.url, x[0]),
title=x[1])
if not validUrl in article['url']:
#无效URL
continue
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}',
'gbk')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl, '图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recDate = re.compile(self.reDate, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}', 'gbk')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=Spider.ComposeUrl(self.url, x[0]),
title=x[1].strip())
for w in recDate.findall(article['url']):
try:
article['time'] = datetime.datetime.strptime(
w, '%Y%m%d%H%M%S')
except Exception as e:
logging.warn('文章源{0}无法识别发布日期，异常为:{1}'.format(
article['url'], str(e)))
continue
# logging.debug(str(article))
if not 'time' in article:
#不符合格式的外部链接忽略
continue
if not self.CheckNewArticle(article):
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}',
'gbk')
if html == None:
continue
content = None
images = []
imageCount = 0
for y in recArticle.findall(html):
#图片过滤
content = recImage.sub(lambda matchobj: '', y)
if not content \
or imageCount != len(images):
continue
self.CacheArticle(article, content, images, '成功自{0}提取文章')
return self.articles
def CatchArticles(self):
recAbstract = re.compile(self.reAbstract, re.DOTALL)
recArticle = re.compile(self.reArticle, re.DOTALL)
recImage = re.compile(self.reImage, re.DOTALL)
recKeyword = re.compile(self.reKeyword, re.DOTALL)
recDate = re.compile(self.reDate, re.DOTALL)
recPage = re.compile(self.rePage, re.DOTALL)
html = self.DownLoadHtml(self.url, '文章列表页{0}访问失败，异常信息为:{1}', 'gbk')
if html == None:
return self.articles
for x in recAbstract.findall(html):
article = dict(url=Spider.ComposeUrl(self.url, x[0]), title=x[1])
if recKeyword.match(x[1]) == None:
#关键词检查
continue
for w in recDate.findall(article['url']):
try:
article['time'] = datetime.datetime.strptime(w, '%Y/%m/%d')
except Exception as e:
logging.warn('文章源{0}无法识别发布日期，异常为:{1}'.format(
article['url'], str(e)))
continue
if not 'time' in article:
#链接日期检查
continue
if not self.CheckNewArticle(article):
#新文章检查
logging.debug('文章源{0}并非新文章。'.format(article['url']))
continue
html = self.DownLoadHtml(article['url'], '文章页{0}访问失败，异常信息为:{1}',
'gbk')
if html == None:
continue
totalContent = ''
images = []
imageCount = 0
pageUrls = [article['url']] + recPage.findall(html)
for p in pageUrls:
pageUrl = Spider.ComposeUrl(article['url'], p)
if pageUrl != article['url']:
html = self.DownLoadHtml(pageUrl, '文章页{0}访问失败，异常信息为:{1}',
'gbk')
if html == None:
continue
content = None
for y in recArticle.findall(html):
content = y
for z in recImage.findall(content):
imageCount += 1
imageUrl = Spider.ComposeUrl(article['url'], z)
image = self.DownLoadImage(imageUrl,
'图片{0}提取失败，异常信息为:{1}')
if image == None:
continue
images.append(image)
if content != None:
totalContent += content
if totalContent == '' \
or imageCount != len(images):
continue
self.CacheArticle(article, totalContent, images, '成功自{0}提取文章')
return self.articles
