def _ana_info_misc(self, hxs): result = {} for string in hxs.extract(): for var, p in self.info_misc_patterns.items(): match = p.search(string) if match: value = match.group(1) result[var] = value author = result.get('author', '') site_name = result.get('site_name', '') view_count = result.get('view_count', 0) reply_count = result.get('reply_count', 0) view_count = try_int_or_0(view_count) reply_count = try_int_or_0(reply_count) return author, site_name, view_count, reply_count
def _ana_misc1(self, hxs): result = {} for string in hxs.extract(): for var, p in self.misc1_patterns.items(): match = p.search(string) if match: value = match.group(1) result[var] = value break zan = result.get('zan_count', 0) zhuanfa = result.get('zhuanfa_count', 0) pinglun = result.get('pinglun_count', 0) zan = try_int_or_0(zan) zhuanfa = try_int_or_0(zhuanfa) pinglun = try_int_or_0(pinglun) return zan, zhuanfa, pinglun