def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://www.baidu.com'
# 当前类还没初始化结束，传给其他类的self会有问题，因此对于要传递self的类都不能在init初始化
self.baidutieba = None
self.baidutieba2 = None
def __init__(self):
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://www.bilibili.com/'
self.queryUrl = 'http://search.bilibili.com/ajax_api/video?keyword={keyword}&page={page}&order=totalrank'
#self.pageUrl = 'http://search.bilibili.com/all?keyword={keyword}&page={page}&order=totalrank'
self.STEP_PAGES = None
self.STEP_VIDEOS = 1
def __init__(self, parent=None):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://donghua.dmzj.com/'
self.r = RegexUtility()
if parent:
self.website = parent.website
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://video.sohu.com/'
self.QUERY_TEMPLATE = 'http://so.tv.sohu.com/mts?wd={key}&flag={flag}&c={c}&length={length}&v={v}&limit={limit}&p={page}&o={o}'
self.DEFAULT_PAGE_SIZE = 20
self.S2QUERY_DEFAULT = 'S2QUERY_ORIGINAL_PAGE'
self.S2QUERY_FIRST_PAGE = 'S2QUERY_FIRST_PAGE'
self.S2QUERY_EACH_PAGE = 'S2QUERY_EACH_PAGE'
def __init__(self):
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://v.qq.com'
# 当前类还没初始化结束，传给其他类的self会有问题，因此对于要传递self的类都不能在init初始化
self.tvtencent = None
self.actencent = None
self.ebooktencent = None
self.postqqbooktencent = None
self.newstencent = None
def __init__(self, parent=None):
"""Constructor"""
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://book.qq.com/'
self.QUERY_TEMPLATE = 'http://book.qq.com/search/index/wd/{key}/type//ps/{page_size}/p/{page}'
self.DEFAULT_PAGE_SIZE = 30
self.QUERY = None
self.FIRST = 'FIRST'
self.EACH = 'EACH'
if parent:
self.website = parent.website
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://search.tianya.cn/bbs?'
self.QUERY_TEMPLATE = 'http://search.tianya.cn/bbs?q={key}&pn={page}&s=6&f=3'
self.DEFAULT_PAGE_SIZE = 75
self.DAYS = 7
self.S2QUERY_FIRST_PAGE = 'S2QUERY_FIRST_PAGE'
self.S2QUERY_SECOND_PAGE = 'S2QUERY_SECOND_PAGE'
self.S2QUERY_EACH_PAGE = 'S2QUERY_EACH_PAGE'
def __init__(self):
SiteS2Query.__init__(self)
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
self.fakeoriginalurl = 'http://baozou.com/'
self.queryUrl = 'http://zhannei.baidu.com/cse/search?q={keyword}&p={page}&s=8807869111209310469&entry=1'
self.pageUrl = self.queryUrl
self.maxPage = 76
self.pageSize = 10.0
self.STEP_PAGES = None
self.STEP_ARTICLES_OR_VIDEOS = 1
self.reArticle = '^http://baozou\.com/articles/\S*'
self.reVideo = '^http://baozou\.com/videos/\S*'
def __init__(self, post_url, parent=None):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = post_url
self.r = RegexUtility()
#self.post_url = BBSS2PostQuery.POST_URL
self.post_url = post_url
self.queryinfo = ''
if parent:
self.website = parent.website
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'Accept-Encoding': 'gzip, deflate, sdch'
}
def __init__(self, parent=None):
"""Constructor"""
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://ac.qq.com/'
self.ORIGINAL_QUERY_TEMPLATE = 'https://v.qq.com/x/search/?q={key}'
self.QUERY_TEMPLATE = 'https://v.qq.com/x/search/?ses={session}&q={key}&filter={ufilter}&cur={page_size}'
self.AC_QUERY_TEMPLATE = 'http://ac.qq.com/Comic/searchList/search/{key}/page/{page_size}'
self.QUERY_TEMPLATE_FILTER = 'sort={0}&pubfilter={1}&duration={2}&tabid={3}'
self.DEFAULT_PAGE_SIZE = 28
self.AC_QUERY = None
self.AC_FIRST = 'AC_FIRST'
self.AC_EACH = 'AC_EACH'
if parent:
self.website = parent.website
def __init__(self, parent=None):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://v.qq.com/'
self.ORIGINAL_QUERY_TEMPLATE = 'https://v.qq.com/x/search/?q={key}'
self.QUERY_TEMPLATE = 'https://v.qq.com/x/search/?ses={session}&q={key}&filter={ufilter}&cur={page_size}'
self.AC_QUERY_TEMPLATE = 'http://ac.qq.com/Comic/searchList/search/{key}/page/{page_size}'
self.QUERY_TEMPLATE_FILTER = 'sort={0}&pubfilter={1}&duration={2}&tabid={3}'
self.DEFAULT_PAGE_SIZE = 28
#searchid表示时间，一周内时设置为9，orderby表示最新回复时间，kw表示搜索关键字，page表示页面
#self.BOOK_QUERY_TEMPLATE = 'http://bbs.book.qq.com/search.php?mod=forum&searchid={searchid}&orderby=lastpost&ascdesc=desc&searchsubmit=yes&kw={key}&p={page}'
self.TV_FIRST = 'TV_FIRST'
self.TV_SECOND = 'TV_SECOND'
self.TV_EACH = 'TV_EACH'
if parent:
self.website = parent.website
def __init__(self):
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://bbs.gfan.com.cn/android-8342764-1-1.html'
self.page_size = 10
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://www.52tian.net/'
self.querylastdays = SpiderConfigure.getinstance().getlastdays()
self.r = RegexUtility()
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://my.hupu.com/'
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://video.sina.com.cn/'
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://v.ifeng.com/'
def __init__(self, parent=None):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://www.duowan.com/'
if parent:
self.website = parent.website
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://forum.home.news.cn/'
self.r = RegexUtility()
def __init__(self):
"""Constructor"""
SiteS2Query.__init__(self)
self.post_url = 'http://bbs.dmzj.com/search.php?mod=forum'
self.get_url = 'http://donghua.dmzj.com'
pass
def __init__(self):
SiteS2Query.__init__(self)
self.r = RegexUtility()
self.fakeoriginalurl='http://www.renren001.cc/search/serach'
self.querylastdays = SpiderConfigure.getinstance().getlastdays()
def __init__(self):
SiteS2Query.__init__(self)
self.r = RegexUtility()
self.fakeoriginalurl = 'http://www.acfun.cn/v/'
self.querylastdays = SpiderConfigure.getinstance().getlastdays()
def __init__(self, parent):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'https://tieba.baidu.com'
self.r = RegexUtility()
self.website = parent.website
def __init__(self):
SiteS2Query.__init__(self)
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
self.fakeoriginalurl = 'http://v.huya.com/'
self.querylastdays = SpiderConfigure.getinstance().getlastdays()
self.r = RegexUtility()
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http[s]{0,1}://www.fun.tv/'
def __init__(self):
SiteS2Query.__init__(self)
self.r = RegexUtility()
self.fakeoriginalurl = 'http://cartoon.pptv.com/'
def __init__(self):
SiteS2Query.__init__(self)
self.r = RegexUtility()
self.pagelimit = self.maxpages
self.fakeoriginalurl = 'http://bbs.pcgames.com.cn/topic-7979.html'
self.querylastdays = SpiderConfigure.getinstance().getlastdays()
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://comic.ku6.com'
self.r = RegexUtility()
def __init__(self,parent=None):
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://news.sogou.com'
self.page_size = 10
if parent:
self.website = parent
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://www.narutom.com/'
self.r = RegexUtility()
def __init__(self):
# 使用该URL识别回传S2查询结果的类，推荐使用主站URL
SiteS2Query.__init__(self)
self.fakeoriginalurl = 'http://bbs.laohu.com/'
self.r = RegexUtility()
self.inputtime = self.querylastdays